Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 50
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Mind the memory gap: unveiling GPU bottlenecks in large-batch LLM inference

  • Garcia Recasens, Pol|||0009-0008-5535-0012
  • Agulló López, Ferran|||0000-0002-7276-2472
  • Zhu, Yue
  • Wang, Changyang
  • Lee, Eun Kyung
  • Tardieu, Olivier
  • Torres Tomás, Juan José
  • Berral García, Josep Lluís|||0000-0003-3037-3580
Large language models have been widely adopted across different tasks, but their auto-regressive generation nature often leads to inefficient resource utilization during inference. While batching is commonly used to increase throughput, per-formance gains plateau beyond a certain batch size, especially with smaller models, a phenomenon that existing literature typically explains as a shift to the compute-bound regime. In this paper, through an in-depth GPU-level analysis, we reveal that large-batch inference remains memory-bound, with most GPU compute capabilities underutilized due to DRAM bandwidth saturation as the primary bottleneck. To address this, we propose a Batching Configuration Advisor (BCA) that optimizes memory allocation, reducing GPU memory requirements with minimal impact on throughput. The freed memory and underutilized GPU compute capabilities can then be leveraged by concurrent workloads. Specifically, we use model replication to improve serving throughput and GPU utilization. Our findings challenge conventional assumptions about LLM inference, offering new in-sights and practical strategies for improving resource utilization, particularly for smaller language models., This work has been partially financed by grant agreement EU-HORIZON GA.101095717 and by the EU-HORIZON MSCA programme under grant agreement EU-HORIZON MSCA GA.101086248. Also, it has been partially financed by Generalitat de Catalunya (AGAUR) under grant agreement 2021-SGR-00478, by Severo Ochoa Center of Excellence CEX-2021-001148-S-20-3, and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OBI00, MCIN/AEI/10.13039/ 501100011033/ FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Mobility usecase: intelligent service migration in cloud-edge continuum

  • Liu, Peini|||0000-0003-0058-8732
  • Oliveras Torra, Joan
  • Palacín Marfil, Marc
  • Dalgitsis, Michail|||0000-0001-8660-0813
  • Serrano, María A.
  • Datsika, Eftychia
  • Antonopoulos, Angelos|||0000-0002-3546-1080
  • Santaella Sánchez, Javier
  • Guitart Fernández, Jordi|||0000-0003-0751-3100
  • Berral García, Josep Lluís|||0000-0003-3037-3580
  • Nou Castell, Ramon|||0000-0003-0464-1473
As industries increasingly embrace digital and intelligent transformation, enterprises face significant challenges in the containerization upgrades for their Artificial Intelligence(AI) applications and dynamic service migration and management in Cloud-Edge continuum(CEC). This paper presents CloudSkin, an innovative platform designed to realize streamlined, seamless and intelligent service migration in Cloud-Edge Continuum by integrating advanced containerization techniques and AI-driven orchestration capabilities. Our approach, leveraging intelligent algorithms for service migration, can seamlessly transit services between cloud and edge environments, ensuring optimised resource allocation and reducing service latency to assure quality of service(QoS). CloudSkin has been enabled in a Mobility Usecase, empowering Cellnex businesses undergoing digital transformation to achieve higher operational efficiency. The experimental results show that compared to traditional reactive service migration, using intelligent proactive service migration can provide better migration detection, improving F1-Score up to 23.5%, and reducing 28.9% the service running time where the service latency violates SLA., This work is financed by the EU-HORIZON programme under grant agreements EU-HORIZON GA.101092646, EU-HORIZON MSCA GA.101086248, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Dexter: a performance-cost efficient resource allocation manager for serverless data analytics

  • Nestorov, Anna Maria
  • Marrón Vida, Diego
  • Gutiérrez Torre, Alberto|||0000-0002-5548-3359
  • Wang, Chen
  • Misale, Claudia
  • Youssef, Alaa
  • Carrera Pérez, David|||0000-0003-4898-3424
  • Berral García, Josep Lluís|||0000-0003-3037-3580
Leveraging serverless platforms for the efficient execution of distributed data analytics frameworks, such as Apache Spark [ 3], has gained substantial interest since early 2022. The elasticity, free-of-management, and on-demand scalability of serverless have motivated the effort in deploying distributed data analytics applications to serverless platforms. However, effectively auto-scaling resources for such complex workloads so that we can fully benefit from the resource elasticity of serverless remains challenging. Mis-configuration can result in severe performance and cost issues arising from resource under- and over-provisioning. In this paper, we present Dexter, a robust resource allocation manager dynamically allocating resources at a fine-grained level to guarantee performance-cost efficiency (optimizing total runtime cost). Dexter is novel in combining predictive and reactive strategies that fully leverage the elasticity of serverless to enhance the performance-cost efficiency for workflow executions. Unlike blackbox ML models, Dexter quickly reaches a sufficiently good solution, prioritizing simplicity, generality, and ease of understanding. Our experimental evaluation shows that, compared with the default serverless Spark resource allocation that dynamically requests exponentially more executors to accommodate pending tasks, our solution achieves a cost reduction of up to 4.65×, while improving performance-cost efficiency up to 3.50×. Dexter also enables a substantial resource saving, demanding up to 5.75× fewer resources., This work is financed by the EU-HORIZON programme under grant agreements EU-HORIZON GA.101092646, EU-HORIZON MSCA GA.101086248, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Towards generalizable Federated Learning in medical imaging: a real-world case study on mammography data

  • Tzortzis, Ioannis N.
  • Gutiérrez Torre, Alberto|||0000-0002-5548-3359
  • Sykiotis, Stavros
  • Agulló López, Ferran|||0000-0002-7276-2472
  • Bakalos, Nikolaos
  • Doulamis, Anastasios
  • Doulamis, Nikolaos
  • Berral García, Josep Lluís|||0000-0003-3037-3580
Federated Learning has been rapidly gaining in popularity in medical applications, due to the increased privacy offered, since medical data doesn't need to leave the hospitals' premises for AI model training. However, a direct translation of a classic experiment to a federated one is not always straightforward. In this work, we delve into the intricacies of federated learning for a breast cancer classification tool. We compare classic model training with a federated variant, and highlight the adaptations that need to be taken care of to ensure the equivalence between the two. Specifically, we introduce the Breast Area Detection tool as an essential component of the pre-processing pipeline to enhance the robustness of Federated Learning by offering data harmonization. On top of that, we present an end-to-end Federated Learning framework that is effective for real-world data and scenarios. Among the three real-world hospitals involved in the experimental procedure, the proposed framework significantly improves performance at the first hospital, providing consistent results similar to those achieved in the classic approach. Experimental results demonstrate that the interventions introduced improved model performance by approximately 35%, aligning federated learning and centralized model performance., This paper is funded by the EU funded projects SECURED “Scaling Up Secure Processing, Anonymization And Generation Of Health Data For EU Cross Border Collaborative Research And Innovation” with grant agreement no. 101095717 and INCISIVE “A multimodal AI-based toolbox and an interoperable health imaging repository for the empowerment of imaging analysis related to the diagnosis, prediction and follow-up of cancer” with grant agreement no. 952179. This paper has been partially financed by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, Severo Ochoa Center of Excellence CEX-2021-001148-S-20-3, 2021- SGR-00478, UE, also Generalitat de Catalunya (AGAUR) under grant agreement 2021-SGR-00478., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Inverse geo-electromagnetic modeling: a systematic review and bibliometric assessment

  • Castillo Reyes, Octavio|||0000-0003-4271-5015
  • Jiménez Andrade, José Luis
  • Dehiya, Rahul
  • Iturraràn Viveros, Ursula
Inverse electromagnetic (EM) modeling plays a pivotal role in subsurface exploration, enabling the characterization of the Earth’s electrical properties for various applications, including resource exploration, environmental monitoring, and geohazard assessment. Despite significant advancements in the field, the EM inverse problem remains inherently challenging due to its ill-posed and nonlinear nature. A diverse range of methodologies, including deterministic, non-deterministic, and machine learning-based (ML-based) approaches, have been proposed to address these challenges. However, there is a lack of a comprehensive synthesis that integrates both the theoretical evolution of these methods and their bibliometric performance. This paper addresses this gap by combining a systematic review of modern computational methodologies with a bibliometric assessment of the scientific literature on inverse EM modeling. The systematic review critically evaluates key computational approaches, examining their theoretical foundations, practical applications, and limitations, while the bibliometric assessment provides a quantitative assessment of scientific productivity, trends, and contributions from different nations. This integrated perspective offers a unified overview of the field, identifies emerging research directions, and highlights the state-of-the-art in inverse EM modeling. The findings provide valuable insights for researchers, practitioners, and policymakers, guiding future advancements and fostering interdisciplinary collaboration., The work of OC have received funding from the MCIN/AEI/10.13039/501100011033 (Spain) and from the European Union NextGenerationEU/PRTR under the project GEOTHERPAL-EM_TED2021-131882B-C42 and -C41. OC has also been partially financed by Generalitat de Catalunya (AGAUR) under grant agreement 2021-SGR-00478. JJA has received support form DGAPA-UNAM IN310325. UI-V was partially supported by JST SATREPS Japan Grant Number JPMJSA2310; DGAPA-UNAM project numbers: IN111823, IN107720 and CONAHCYT México under Ciencia de Frontera Project Number: 6655. Finally, this work has been partially financed by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE. Authors thanks to Josep Ll. Berral (UPC) and the CROMAI team (UPC) for their support on this research., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

On the relation between open project-based learning in undergraduate computer science education and contemporary technological trends

  • Tous Liesa, Rubén|||0000-0002-1409-5843
  • Freitag, Fèlix|||0000-0001-5438-479X
  • Berral García, Josep Lluís|||0000-0003-3037-3580
Amidst rapid and constant technological change, keeping IT higher education curricula up to date is becoming increasingly challenging. For a decade, the course”Project on Information Technologies” within the undergraduate computer science studies offered by a major technical university has been pursuing an effort of continuous curriculum adaptation and active learning practices based on an open project-based learning (PBL) methodology. This article researches the implications of employing an open-ended PBL approach, with a specific focus on the alignment of acquired skills with the trends in the professional landscape. Our analysis has identified a strong correlation between the technologies utilized in the projects and the contemporary technological trends in the areas of global technological focus, programming languages, server-side technologies, database management systems, and DevOps-related tools. For the study, we analyzed empirical data gathered from over 100 projects involving more than 400 students who enrolled in this reference course, belonging to the last year of the IT higher education programme in the last 10 years. The results suggest the open project-based design as a teaching means in the student’s study plan for fostering the student the learning of prevailing current practical technologies., This work is partially supported by the Span-ish Ministry of Science under contracts PID2019-107255GB, PID2019-106774RB-C21, PID2021-126248OB-I00 (MCIN/AEI/10.13039/501100011033/FEDER), PDC2023-145809-I00 (PDC/AEI/10.13039/501100011033), the Recovery and Resilience Facility of the European Union, and by the SGR programme of the Catalan Government under contracts 2021-SGR-00478 and 2021-SGR-01059., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

In-context bias propagation in LLM-based tabular data generation

  • Garcia Recasens, Pol|||0009-0008-5535-0012
  • Gutiérrez Torre, Alberto|||0000-0002-5548-3359
  • Torres Viñals, Jordi|||0000-0003-1963-7418
  • Berral García, Josep Lluís|||0000-0003-3037-3580
  • Halimi, Anisa
  • Fraser, Kieran
Large Language Models (LLMs) are increasingly used for synthetic tabular data generation through in-context learning (ICL), offering a practical solution for data augmentation in data scarce scenarios. While prior work has shown the potential of LLMs to improve downstream task performance through augmenting underrepresented groups, these benefits often assume access to a subset of unbiased in-context examples, representative of the real dataset. In real-world settings, however, data is frequently noisy and demographically skewed. In this paper, we systematically study how statistical biases within in-context examples propagate to the distribution of synthetic tabular data, showing that even mild in-context biases lead to global statistical distortions. We further introduce an adversarial scenario where a malicious contributor can inject bias into the synthetic dataset via a subset of in-context examples, ultimately compromising the fairness of downstream classifiers for a targeted and protected subgroup. Finally, we evaluate mitigation strategies based on preprocessing in-context examples, demonstrating that while such interventions can attenuate disparity, the inherent sensitivity of LLMs to adversarial prompts remains a persistent challenge. Our findings highlight a critical new vulnerability in LLM-based data generation pipelines within sensitive domains, This work has been partially financed by grant agreement EU-HORIZON GA.101095717 and by grant agreement EU-HORIZON MSCA GA.101086248. Also, it has been partially financed by Generalitat de Catalunya (AGAUR) under grant agreement 2021-SGR-00478, by Severo Ochoa Center of Excellence CEX-2021-001148-S20-3, and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/ FEDER, UE. Kieran Fraser and Anisa Halimi were partly supported by the Innovative Health Initiative Joint Undertaking (IHI JU) under grant agreement No. 101172997– SEARCH., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Feature engineering for agents: an adaptive cognitive architecture for interpretable ML monitoring

  • Bravo Rocca, Gusseppe Jesus|||0000-0001-6824-1124
  • Liu, Peini|||0000-0003-0058-8732
  • Guitart Fernández, Jordi|||0000-0003-0751-3100
  • Carrillo Larco, Rodrigo M.
  • Dholakia, Ajay
  • Ellison, David
Monitoring Machine Learning (ML) models in production environments is crucial, yet traditional approaches often yield verbose, low-interpretability outputs that hinder effective decision-making. We propose a cognitive architecture for ML monitoring that applies feature engineering principles to agents based on Large Language Models (LLMs), significantly enhancing the interpretability of monitoring outputs. Central to our approach is a Decision Procedure module that simulates feature engineering through three key steps: Refactor, Break Down, and Compile. The Refactor step improves data representation to better capture feature semantics, allowing the LLM to focus on salient aspects of the monitoring data while reducing noise and irrelevant information. Break Down decomposes complex information for detailed analysis, and Compile integrates sub-insights into clear, interpretable outputs. This process leads to a more deterministic planning approach, reducing dependence on LLM-generated planning, which can sometimes be inconsistent and overly general. The combination of feature engineering-driven planning and selective LLM utilization results in a robust decision support system, capable of providing highly interpretable and actionable insights. Experiments using multiple LLMs demonstrate the efficacy of our approach, achieving significantly higher accuracy compared to various baselines across several domains., This work was partially supported by Lenovo and Intel® as part of the Lenovo AI Innovators University Research program, by Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under contracts PID2019- 107255GB-C22 and PID2021-126248OB-I00, and by the Generalitat de Catalunya (AGAUR) under contract 2021-SGR-00478., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Embedded scaffolding for teaching and assessing inquiry-based hands-on laboratory on distributed systems

  • Guitart Fernández, Jordi|||0000-0003-0751-3100
Context Information Technology education must cultivate proficiency on distributed systems, including strong hands-on laboratory skills, to meet the needs of the society and the industry. Given the complexity of distributed systems, any successful methodology to teach them to novice students must be scaffolded appropriately to ensure that the students acquire the required degree of expertise. Objective We propose a comprehensive scaffolding approach for inquiry-based hands-on laboratory on a distributed systems course, which guides not only the learning process, but also its assessment. The approach is based mainly on embedded scaffolds, namely explicit coding and experimental milestones and open questions with predefined grades, but also features contingent scaffolds provided by the teacher when additional assistance is needed. Method We apply the methodology in the context of the subject ‘Distributed Network Systems’ offered by our university. We compare the students' performance during three academic courses using the proposed methodology with respect to the three previous courses that were still using the former methodology. We use both visual representations and planned Analysis of Variance (ANOVA) tests to verify our hypothesis defined as a complex contrast. Findings We find that there is a statistically significant improvement in the students' performance when using the new methodology, both in their grades of the assignments (F(1, 75.364) = 17.770, p = 6.85*10^-5) and, more importantly, also in their grades of the exam questions about the practicals (F(1, 123.186) = 13.285, p = 3.93*10^-4). Implications Our results encourage other instructors to incorporate embedded scaffolds for teaching and assessing their hands-on laboratories on distributed systems., This research was partially supported by the Agencia Estatal de Investigación under contracts PID2019-107255GB-C22 and PID2021-126248OB-I00 and by the Generalitat de Catalunya under contract 2021-SGR-00478., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Time-quality tradeoff of MuseHash query processing performance

  • Pegia, Maria
  • Agulló López, Ferran|||0000-0002-7276-2472
  • Moumtzidou, Anastasia
  • Gutiérrez Torre, Alberto|||0000-0002-5548-3359
  • Jónsson, Björn Þór
  • Berral García, Josep Lluís|||0000-0003-3037-3580
  • Gialampoukidis, Ilias
  • Vrochidis, Stefanos
  • Kompatsiaris, Ioannis
Nowadays, large quantities of multimedia data are generated by various applications on smartphones, drones and other devices. Facilitating retrieval from these multimedia collections requires (a) effective media representation and (b) efficient indexing and query processing approaches. Recently, the MuseHash approach was proposed, which can effectively represent a variety of modalities, improving on previous hashing-based approaches. However, the interaction of the MuseHash approach with existing indexing and query processing approaches has not been considered. This paper provides the first systematic evaluation of the time-quality tradeoff that arises when MuseHash media representation is combined with state-of-the-art approximate nearest-neighbour indexes along multi-core and GPU processing., The work reported here was supported by the EU’s Horizon 2020 research and innovation programme under grant agreements H2020-101070250 CALLISTO, H2020-101070262 WATERVERSE, and H2020-101080090 ALLIES, and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreements PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE, Severo Ochoa Center of Excellence CEX2021-001148-S-20-3 and the Generalitat de Catalunya (AGAUR) 2021-SGR-00478., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Scalable energy-aware VM allocation on cloud data centers through mathematical programming models

  • Meroni, Roberto
  • Guitart Fernández, Jordi|||0000-0003-0751-3100
Cloud data centers are becoming indispensable pillars of modern society, driving AI innovation, global connectivity, and data-driven advancements. As their size and complexity grow, so does the urgency for sustainable and efficient solutions to address operational and environmental challenges. The Virtual Machine (VM) allocation problem lies at the heart of these challenges, directly impacting energy consumption, scalability, and cost-effectiveness. While heuristics are traditionally favored for their fast execution times, they fail to adequately address the complexities of heterogeneous environments and the increasing need for energy-aware solutions. In this work, we redefine the potential of mathematical programming models — traditionally considered impractical due to scalability limitations — by defining a comprehensive VM allocation strategy that embeds the models into scalable algorithms that distribute computational workloads and exploit solver capabilities. This approach achieves linear scalability — an unprecedented milestone for mathematical programming — allowing us to integrate detailed and heterogeneous aspects of the VM allocation problem. The resulting algorithms dramatically outperform state-of-the-art heuristics and metaheuristics in both scalability and solution quality, delivering an average 16% increase in Net Profit, a 54% reduction in Total Energy Consumption, and a more-than-double improvement in Energy Efficiency. Designed to meet the evolving demands of modern Cloud data centers, our algorithms scale efficiently to manage growing workloads, adapt to heterogeneity, and comply with sustainability and regulatory requirements by prioritizing energy efficiency, facilitating the transition to next-generation Cloud environments., This research was partially supported by the EU-HORIZON programme under grant agreement EU-HORIZON GA.101092646, by the Spanish Ministry of Science and the Research State Agency (MICIU/AEI/ 10.13039/501100011033) and by European Regional Development Funds (ERDF/FEDER) under contract PID2021-126248OB-I00, and by the Generalitat de Catalunya (AGAUR) under contract 2021-SGR-00478., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Integrating reliability into intent-driven orchestration on kubernetes-based edge nodes

  • Berral García, Josep Lluís|||0000-0003-3037-3580
  • Aguilera Luzón, David|||0009-0001-1302-9000
  • Liu, Peini|||0000-0003-0058-8732
  • Nou Castell, Ramon|||0000-0003-0464-1473
  • Serrano, María A.
  • Antonopoulos, Angelos|||0000-0002-3546-1080
  • Santaella Sánchez, Javier
  • Divan Koller, Mario José
Placing workloads across the Edge and Cloud can be performed through containerization. However, conditions in Edge nodes are very different from Cloud, as environmental factors such as temperature, humidity, voltage provisioning or dust, heavily affect execution performance and device health. Reliability is an important factor when deciding to deploy such load onto Edge devices, indicating their capability to achieve a desired Quality of Service (QoS). For this, research on Edge computing must focus on how to monitor, estimate and manage devices, in a distributed, autonomous and reliable manner. Our current efforts on performance analysis for devices under "wild conditions" are moving towards integrating reliability into orchestrator systems. Here we present our vision and roadmap for expanding Cloud orchestration towards the Edge with technologies capable of providing knowledge about node environmental conditions and mitigate its impact. Through Out-Of-Band telemetry, we can retrieve temperature and power consumption variables from node components, indicating its health and estimating its reliability given external stress factors. In particular, using intent-based orchestration for containerized platforms, such factors can be used for enforcing reliability as a key-performance indicator. The current work in progress focuses on industrial and commercial scenarios, e.g., Edge computing for urban mobility, with road-side nodes performing AI-based Video-Analytics, exposed to uncontrolled weather conditions. The principal objective is to achieve an Edge network orchestration that takes into account node health in an automatic manner for reducing operational costs such as energy consumption, device repair and replacement, while maintaining QoS in the Edge., This work is financed by the INTEL UFunding #14780, the EU-HORIZON and MSCA programmes under GA.101092646 and GA.101086248, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Experience replay and zero-shot clustering for continual learning in diabetic retinopathy detection

  • Bravo Rocca, Gusseppe Jesus|||0000-0001-6824-1124
  • Liu, Peini|||0000-0003-0058-8732
  • Guitart Fernández, Jordi|||0000-0003-0751-3100
  • Dholakia, Ajay
  • Ellison, David
  • Carrillo Larco, Rodrigo M.
We present an approach to mitigate catastrophic forgetting in Continual Learning (CL), focusing on domain incremental scenarios in medical imaging. Our method leverages Large Language Models (LLMs) to generate task-agnostic descriptions from multimodal inputs, enabling zero-shot clustering of tasks without supervision. This clustering underpins an enhanced Experience Replay (ER) strategy, strategically sampling data points to refresh the model’s memory while preserving privacy. By incrementally updating a multi-head classifier using only data embeddings, our approach maintains both efficiency and data confidentiality. Evaluated on a challenging diabetic retinopathy dataset, our method demonstrates significant improvements over traditional CL techniques, including Elastic Weight Consolidation (EWC), Gradient Episodic Memory (GEM), and Learning Without Forgetting (LWF). Extensive experiments across Multi-Layer Perceptron (MLP), Residual, and Attention architectures show consistent performance gains (up to 3.1% in Average Mean Class Accuracy) and reduced forgetting, with only 6% computational overhead. These results highlight our approach’s potential for privacy-preserving, efficient CL in sensitive domains like healthcare, offering a promising direction for developing adaptive AI systems that can learn continuously while respecting data privacy constraints., This work was partially supported by Lenovo and Intel as part of the Lenovo AI Innovators University Research program, by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreements PID2019-107255GB-C22 and PID2021-126248OBI00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE, and by the Generalitat de Catalunya under contract 2021-SGR-00478.
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Data-Connector: an agent-based framework for autonomous ML-based smart management in cloud-edge continuum

  • Liu, Peini|||0000-0003-0058-8732
  • Oliveras Torra, Joan
  • Palacín Marfil, Marc
  • Guitart Fernández, Jordi|||0000-0003-0751-3100
  • Berral García, Josep Lluís|||0000-0003-3037-3580
  • Nou Castell, Ramon|||0000-0003-0464-1473
Machine Learning (ML) is becoming pervasive and integrated into different kinds of intelligent applications, and the collaborative Cloud-Edge continuum has been introduced as an emerging trend to support their adoption into use cases. However, managing these ML applications in the CloudEdge continuum is challenging due to the ML application's dynamic resource usage with different user loads and Cloud and Edge's dynamic resource availability. We envision machine learning methods that can be used for smart management in this dynamic environment, but how to deploy and utilize them for the adaptation scenario in Cloud-Edge continuum is unknown. This paper proposes an agent-based framework to enable autonomous smart management mechanisms that can be broadly enabled in diverse adaptation scenarios. The agent acts as a data-connector1 1https://github.com/bsc-scanflow/data-connector, connecting different sources of data, utilizing ML models for decision-making and triggering adaptations in Cloud-edge platforms. The case study shows the feasibility of our proposed data-connector for smart migration of an ML workload in the Cloud-edge continuum. The result shows that the smart migration-enabled Cloud-edge scenario has 11.9% ML application prediction time better than the Cloud scenario without migration. Moreover, with minimal customization, the data connector agent can be adapted for more use cases., This work is financed by the EU-HORIZON programme under grant agreements EU-HORIZON GA.101092646, EU-HORIZON MSCA GA.101086248, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

FRIDA: Free-rider detection using privacy attacks

  • Garcia Recasens, Pol|||0009-0008-5535-0012
  • Horváth, Ádám
  • Gutiérrez Torre, Alberto|||0000-0002-5548-3359
  • Torres Viñals, Jordi|||0000-0003-1963-7418
  • Berral García, Josep Lluís|||0000-0003-3037-3580
  • Pejó, Balázs|||0000-0002-1825-9251
Federated learning is increasingly popular as it enables multiple parties with limited datasets and resources to train a machine learning model collaboratively. However, similar to other collaborative systems, federated learning is vulnerable to free-riders — participants who benefit from the global model without contributing. Free-riders compromise the integrity of the learning process and slow down the convergence of the global model, resulting in increased costs for honest participants. To address this challenge, we propose FRIDA: free-rider detection using privacy attacks. Instead of focusing on implicit effects of free-riding, FRIDA utilizes membership and property inference attacks to directly infer evidence of genuine client training. Our extensive evaluation demonstrates that FRIDA is effective across a wide range of scenarios., Project no. 145832, implemented with the support provided by the Ministry of Innovation and Technology from the NRDI Fund, financed under the PD_23 funding scheme. Also, partially financed by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI), and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/501100011033/FEDER, UE, and Generalitat de Catalunya (AGAUR) under grant 2021-SGR-00478. Lastly, also funded by the European Union (Grant Agreement Nr. 101095717, SECURED Project)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

A data-driven ML approach for maximizing performance in LLM-adapter serving

  • Agulló López, Ferran|||0000-0002-7276-2472
  • Oliveras Torra, Joan
  • Wang, Chen
  • Gutiérrez Torre, Alberto|||0000-0002-5548-3359
  • Tardieu, Olivier
  • Youssef, Alaa
  • Torres Viñals, Jordi|||0000-0003-1963-7418
  • Berral García, Josep Lluís|||0000-0003-3037-3580
With the rapid adoption of Large Language Models (LLMs), LLM-adapters have become increasingly common, providing lightweight specialization of large-scale models. Serving hundreds or thousands of these adapters on a single GPU allows request aggregation, increasing throughput, but may also cause request starvation if GPU memory limits are exceeded. To address this issue, this study focuses on determining the joint configuration of concurrent and parallel adapters that maximizes GPU throughput without inducing starvation, given heterogeneous adapter and traffic properties. We propose a data-driven ML approach leveraging interpretable models to tackle this caching problem and introduce the first Digital Twin capable of reproducing an LLM-adapter serving system, enabling efficient training data generation. Experiments with the vLLM framework and LoRA adapters show that the Digital Twin reproduces throughput within 5.1% of real results, while the ML approach predicts optimal numbers of concurrent and parallel adapters with an error of at most 7.2% under heterogeneous, real-world workloads., This work has been partially financed by the EU-HORIZON MSCA programme under grant agreement EU-HORIZON MSCAGA.101086248. Also, it has been partially financed by Generalitat de Catalunya (AGAUR)under grant agreement 2021-SGR-00478, by Severo Ochoa Center of Excellence CEX-2021-001148-S-20-3, and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/ FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Enhancing the output of time series forecasting algorithms for cloud resource provisioning

  • Agulló López, Ferran|||0000-0002-7276-2472
  • Gutiérrez Torre, Alberto|||0000-0002-5548-3359
  • Torres Viñals, Jordi|||0000-0003-1963-7418
  • Berral García, Josep Lluís|||0000-0003-3037-3580
Forecasting the resource consumption of workloads is a frequent approach in the cloud provisioning field. Ideally, such predictions allow obtaining a more accurate scheduling and management of resources in a computing cluster. However, the current approaches fail to properly forecast the future consumption in areas where sudden increases of consumption are present, i.e., spikes. Even, commonly employed metrics lack the ability to properly evaluate sharp behaviours in the traces. This may generate resource starvation problems in the running workloads and decreases the Quality of Service (QoS) provided to external users. To address this issue, we propose two strategies that modify the outputs of forecasting algorithms without changing the algorithms’ internals. The new outputs considerably enhance the prediction of sudden increases, duplicating the F1 score metric in average for all tested algorithms. This improvement in the handling of spikes comes with an increased over-provision of resources. Nevertheless, the proposed strategies give the user an easy way to control this trade-off between predicting spikes and the amount of over-provision. The user can decide which is the right balance that better fits the requirements of its specific scenario. Furthermore, we propose a new evaluation methodology that better assesses the behaviour of forecasting algorithms in cloud traces, especially focused on the performance around increases of consumption, and we give insights on the reasons behind the predictions of the algorithms with the application of explainability techniques. The code repository of this work can be accessed through GitHub at this link https://github.com/FerranAgulloLopez/ResourceForecasting., This work has been supported by the EU’s Horizon research and innovation programme under grant agreements HORIZON GA.101092646 (CloudSkin), HORIZON MSCA GA.101086248 (CloudStars), and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreements PID-2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033, UE (DALEST), Severo Ochoa Center of Excellence CEX-2021-001148-S-20-3 and the Generalitat de Catalunya (AGAUR), Spain 2021-SGR-00478 (CROMAI)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

SynthVal: A framework for validating synthetic medical images

  • Guidotti, Dario
  • Pandolfo, Laura
  • Gutiérrez Torre, Alberto|||0000-0002-5548-3359
  • López Rúbio, Omar
  • Pulina, Luca
Synthetic data is increasingly used in medical imaging to overcome data scarcity and privacy constraints. However, assessing the fidelity of synthetic images remains a critical challenge for ensuring their safe and effective use in clinical and AI applications. We present SynthVal, a Python-based framework for validating the quality of synthetic medical images through statistical comparisons in deep feature space. SynthVal extracts semantic image embeddings using transformer-based models and computes similarity metrics – including Fréchet Distance, Wasserstein Distance, and Kullback-Leibler Divergence – between real and synthetic data distributions. The framework is designed for modularity, scalability, and ease of integration into existing workflows via pip installation. We evaluate SynthVal using real images from the CSAW-CC dataset, and synthetic images produced by a model developed by the Barcelona Supercomputing Center. Our experiments systematically benchmark the influence of different feature extraction models and similarity metrics, providing practical insights for selecting validation strategies in medical image synthesis. SynthVal offers a reproducible and extensible solution for quality control in synthetic data pipelines., The work of Dario Guidotti, Laura Pandolfo, and Luca Pulina was supported by EU Project SECURED, ‘‘Scaling Up Secure Processing, Anonymization and Generation of Health Data for EU Cross-Border Collaborative Research and Innovation,’’ under Agreement 101095717. The work of Alberto Gutierrez-Torre and Omar Lopez-Rubio was supported by SECURED under Agreement 101095717; in part by Spanish Ministry of Science (MICINN), the State Research Agency (AEI), and European Regional Development Funds (ERDF/FEDER) under Grant PID2021-126248OB-I00; in part by MCIN/AEI/10.13039/501100011033/FEDER, UE; and in part by the Generalitat de Catalunya (AGAUR) under Grant 2021-SGR-00478., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

CloudSkin: ML-based smart management for the cloud-edge continuum

  • Liu, Peini|||0000-0003-0058-8732
  • Nestorov, Anna Maria
  • Palacín Marfil, Marc
  • Nou Castell, Ramon|||0000-0003-0464-1473
  • Guitart Fernández, Jordi|||0000-0003-0751-3100
  • Berral García, Josep Lluís|||0000-0003-3037-3580
The CloudSkin project embraces ML-based autonomous management technologies, introducing the Learning Plane (LP), which provides services and methods to embed intelligence in Cloud-Edge Continuum management layers. By leveraging AI, the continuum can achieve user demands for resource, privacy, resilience, and energy efficiency requirements, in an adaptive way. As a first Proof-of-Concept, we envision a smart orchestrator to drive a 5G-powered automotive usecase, focusing on a mobility scenario where the LP optimises resources for AI data and applications, on a transversal Edge environment., This work is financed by the EU-HORIZON programme under grant agreements EU-HORIZON GA.101092646, EU-HORIZON MSCA GA.101086248, EU-HORIZON GA.101092644, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

GreenWise: intelligent application migration for containerized machine learning services in the computing continuum

  • Liu, Peini|||0000-0003-0058-8732
  • Santos, José
  • De Turck, Filip
  • Guitart Fernández, Jordi|||0000-0003-0751-3100
Machine Learning (ML) services require both responsiveness and efficiency. In the dynamic Computing Continuum (CC), service migration has emerged as an important strategy to optimize service performance, improve power efficiency, or reduce operational costs. A basis enabler of the service migration in the CC is containerization and container orchestration, however, dynamically moving the service among Cloud and Edge servers based on several uncertainties is still challenging. In this paper, we present GreenWise, a framework for intelligent service migration for containerized ML services in the heterogeneous CC. GreenWise extends the monitoring agents to continuously monitor power consumption and performance metrics across diverse layers and sources in real-time, providing a holistic view of states. Leveraging Reinforcement Learning (RL), it enables Power-Performance aware strategies to achieve near-optimal online migration decisions under dynamic conditions. We perform GreenWise on top of a Kubernetes-based CC platform, implementing agents for intelligent migration for containerizedML services. Experimental results demonstrate that GreenWise achieves effective trade-offs between performance and power efficiency. Our proposed Power-Latency-Aware (MaskPPO) migration strategy outperforms Random and Round-Robin baselines 159.2% and 13.8% in a real cluster. These results highlight GreenWise’s potential for sustainable and intelligent ML service migration in the dynamic CC., This work is financed by the EU-HORIZON programme under grant agreements EU-HORIZON CLOUDSKIN GA.101092646, EU-HORIZON SPIRIT GA.101070672, EU-HORIZON MSCA CLOUDSTARS GA.101086248; by the Spanish Ministry of Science (MICINN) PID2021-126248OB-I00, MCIN/AEI/10.13039/501100011033/FEDER, UE and PID2024-160996OB-I00; and by the Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478. José Santos is funded by the Research Foundation Flanders (FWO), grant numbers 1299323N and 1253226N., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

A reliability score for video-analytics edge-IoT devices in urban environments

  • Garcia Boris, Marçal
  • Oliveras Torra, Joan
  • Aguilera Luzón, David|||0009-0001-1302-9000
  • Liu, Peini|||0000-0003-0058-8732
  • Divan Koller, Mario José
  • Berral García, Josep Lluís|||0000-0003-3037-3580
Performing video-analytics in Edge and IoT devices towards urban mobility allows computing near-data, providing fast and autonomous management from streets and roads. Thanks to advances in artificial intelligence methods, real-time classification of camera-provided image feeds can be performed in low-power devices to be deployed next to urban signaling and city services. However, devices deployed “in the wild” are affected by environmental factors such as temperature, either ambient or retained by its container, humidity or voltage changes, coming from sensorized urban furniture. Deciding where to deploy video-analytics workload requires a minimal device performance reliability, assuring that load can be processed in-place, before moving it towards the Fog/Cloud or other nearby devices. Here we present a simplistic factorization of a reliability Score to be quickly computed in Edge nodes, towards orchestrating workload according to the node surrounding environment. The score takes into account ambient temperature and humidity, also received voltage. The scoring is evaluated performing video-analytics workloads on real devices under physical stress, observing the performance degradation related to the external and internal factors applied onto the device. From the study, we observe how the different factors affect the functioning mode and quality of service, aside of indicating an estimation of the reliability of the urban-placed devices., This work is financed by the INTEL UFunding #14780, the EU-HORIZON and MSCA programmes under GA.101092646 and GA.101086248, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

HealthMesh: An architectural framework for federated healthcare data management

  • Bisquert Parés, Aniol
  • Hmimou Ham Man, Achraf|||0009-0004-0448-3406
  • Berral García, Josep Lluís|||0000-0003-3037-3580
  • Gutiérrez Torre, Alberto|||0000-0002-5548-3359
  • Romero Moral, Óscar|||0000-0001-6350-8328
Recently, significant milestones have been achieved in the field of healthcare data analysis. However, alongside these accomplishments, substantial data-related challenges have emerged in the domain of big data management. Modern healthcare projects are no more dealing with a single data repository but many heterogeneous ones and must overcome data variety, privacy and governance issues. Yet, current solutions face a privacy-decentralization trade-off. To address this dual challenge, we introduce HealthMesh, a novel layered architectural framework based on the Data Mesh principles, providing a domaindecentralised paradigm. In addition, the framework incorporates a Semantic Data Model which establishes robust governance, enables interoperability and guarantees policy compliance for all the data assets. To demonstrate the capabilities of the proposed approach, we provide an illustrative example inspired by the use case of the INCISIVE project for breast cancer analytics. Overall, this work makes a significant contribution on collecting key challenges, identifying actors and providing a set of components and guidelines for establishing a holistic framework for the complex field of healthcare data management., The work reported here was supported by the EU-H2020 programme under GA.952179 INCISIVE, Horizon Europe Programme under GA.101095717 (SECURED) and GA.101135513 (CYCLOPS), the Spanish Research State Agency (MICINN/AEI, ERDF/FEDER) under GA.MCIN/AEI/10.13039/501100011033/FEDER (UE DALEST), the Spanish Ministerio de Ciencia e Innovación under project PID2020-117191RB-I00 / AEI/10.13039/501100011033 (DOGO4ML), and the Generalitat de Catalunya (AGAUR) 2021-SGR-00478 (CROMAI)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

MScheduler: leveraging spot instances for high-performance reservoir simulation in the cloud

  • Albuquerque Portella, Felipe|||0000-0003-1245-7465
  • Estrela, Paulo J.B.
  • Malini, Renzo Q.
  • Teylo, Luan
  • Berral García, Josep Lluís|||0000-0003-3037-3580
  • Drummond, Lúcia M.A.
Petroleum reservoir simulation uses computer models to predict fluid flow in porous media, aiding to forecast oil production. Engineers execute numerous simulations with different geological realizations to refine the accuracy of the model. These experiments require considerable computational resources, which are not always available within the on-premises infrastructure. Commercial public cloud platforms can offer many advantages, such as virtually unlimited scalability and payper-use pricing. This paper introduces MSCHEDULER, a meta scheduler framework for reservoir simulations at Petrobras, a Brazilian energy company. It efficiently executes jobs in the cloud, utilizing spot Virtual Machines (VMs) to reduce costs and ensure job completion even with VM termination. Contributions include a novel methodology for reservoir simulation checkpointing, a cost-based scheduler, and an analysis of the strategy using real production jobs from Petrobras., This work was funded by Petroleo Brasileiro S.A. – Petrobras, by Project Universal/CNPq no 404087/2021-3 and CNE/FAPERJ no E-26/201.012/2022(271103). Also by Spanish Ministry of Science (MICINN, AEI, ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE, and Generalitat de Catalunya (AGAUR) 2021-SGR-00478., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Exhaustive variant interaction analysis using multifactor dimensionality reduction

  • Gómez Sánchez, Gonzalo
  • Alonso Parrilla, Lorena
  • Pérez Elena, Miguel Ángel
  • Morán, Ignasi
  • Torrents Arenales, David
  • Berral García, Josep Lluís|||0000-0003-3037-3580
One of the main goals of human genetics is to understand the connections between genomic variation and the predisposition to develop a complex disorder. These disease–variant associations are usually studied in a single independent manner, disregarding the possible effect derived from the interaction between genomic variants. In particular, in a background of complex diseases, these interactions can be directly linked to the disorder and may play an important role in disease development. Although their study has been suggested to help complete the understanding of the genetic bases of complex diseases, this still represents a big challenge due to large computing demands. Here, we take advantage of high-performance computing technologies to tackle this problem by using a combination of machine learning methods and statistical approaches. As a result, we created a containerized framework that uses multifactor dimensionality reduction (MDR) to detect pairs of variants associated with type 2 diabetes (T2D). This methodology was tested on the Northwestern University NUgene project cohort using a dataset of 1,883,192 variant pairs with a certain degree of association with T2D. Out of the pairs studied, we identified 104 significant pairs: two of which exhibit a potential functional relationship with T2D. These results place the proposed MDR method as a valid, efficient, and portable solution to study variant interaction in real reduced genomic datasets., This work was partially financed by the European Commission (EU-HORIZON NEARDATA GA.101092644) and by the Universitat Politècnica de Catalunya (45-FPIUPC2018); it was also partially financed by Generalitat de Catalunya (AGAUR) under grant agreement 2021-SGR-00478; it was also partially financed by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI), and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/501100011033/FEDER, UE., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Towards Pareto optimal throughput in small language model serving

  • Garcia Recasens, Pol|||0009-0008-5535-0012
  • Zhu, Yue
  • Wang, Chen
  • Lee, Eun Kyung
  • Tardieu, Olivier
  • Youssef, Alaa
  • Torres Viñals, Jordi|||0000-0003-1963-7418
  • Berral García, Josep Lluís|||0000-0003-3037-3580
Large language models (LLMs) have revolutionized the state-of-the-art of many different natural language processing tasks. Although serving LLMs is computationally and memory demanding, the rise of Small Language Models (SLMs) offers new opportunities for resource-constrained users, who now are able to serve small models with cutting-edge performance. In this paper, we present a set of experiments designed to benchmark SLM inference at performance and energy levels. Our analysis provides a new perspective in serving, highlighting that the small memory footprint of SLMs allows for reaching the Pareto-optimal throughput within the resource capacity of a single accelerator. In this regard, we present an initial set of findings demonstrating how model replication can effectively improve resource utilization for serving SLMs., This work has been partially financed by grant agreement EUHORIZON GA.101095717 and by the EU-HORIZON MSCA programme under grant agreement EU-HORIZON MSCA GA.101086248. Also, it has been partially financed by Generalitat de Catalunya (AGAUR) under grant agreement 2021- SGR-00478, and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/ 10.13039/ 501100011033/ FEDER, UE., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

GreenWise: intelligent application migration for containerized machine learning services in the computing continuum

  • Liu, Peini
  • Santos, José
  • De Turck, Filip
  • Guitart Fernández, Jordi
Machine Learning (ML) services require both responsiveness and efficiency. In the dynamic Computing Continuum (CC), service migration has emerged as an important strategy to optimize service performance, improve power efficiency, or reduce operational costs. A basis enabler of the service migration in the CC is containerization and container orchestration, however, dynamically moving the service among Cloud and Edge servers based on several uncertainties is still challenging. In this paper, we present GreenWise, a framework for intelligent service migration for containerized ML services in the heterogeneous CC. GreenWise extends the monitoring agents to continuously monitor power consumption and performance metrics across diverse layers and sources in real-time, providing a holistic view of states. Leveraging Reinforcement Learning (RL), it enables Power-Performance aware strategies to achieve near-optimal online migration decisions under dynamic conditions. We perform GreenWise on top of a Kubernetes-based CC platform, implementing agents for intelligent migration for containerizedML services. Experimental results demonstrate that GreenWise achieves effective trade-offs between performance and power efficiency. Our proposed Power-Latency-Aware (MaskPPO) migration strategy outperforms Random and Round-Robin baselines 159.2% and 13.8% in a real cluster. These results highlight GreenWise’s potential for sustainable and intelligent ML service migration in the dynamic CC., This work is financed by the EU-HORIZON programme under grant agreements EU-HORIZON CLOUDSKIN GA.101092646, EU-HORIZON SPIRIT GA.101070672, EU-HORIZON MSCA CLOUDSTARS GA.101086248; by the Spanish Ministry of Science (MICINN) PID2021-126248OB-I00, MCIN/AEI/10.13039/501100011033/FEDER, UE and PID2024-160996OB-I00; and by the Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478. José Santos is funded by the Research Foundation Flanders (FWO), grant numbers 1299323N and 1253226N., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Experience replay and zero-shot clustering for continual learning in diabetic retinopathy detection

  • Bravo Rocca, Gusseppe Jesus
  • Liu, Peini
  • Guitart Fernández, Jordi
  • Dholakia, Ajay
  • Ellison, David
  • Carrillo Larco, Rodrigo M.
We present an approach to mitigate catastrophic forgetting in Continual Learning (CL), focusing on domain incremental scenarios in medical imaging. Our method leverages Large Language Models (LLMs) to generate task-agnostic descriptions from multimodal inputs, enabling zero-shot clustering of tasks without supervision. This clustering underpins an enhanced Experience Replay (ER) strategy, strategically sampling data points to refresh the model’s memory while preserving privacy. By incrementally updating a multi-head classifier using only data embeddings, our approach maintains both efficiency and data confidentiality. Evaluated on a challenging diabetic retinopathy dataset, our method demonstrates significant improvements over traditional CL techniques, including Elastic Weight Consolidation (EWC), Gradient Episodic Memory (GEM), and Learning Without Forgetting (LWF). Extensive experiments across Multi-Layer Perceptron (MLP), Residual, and Attention architectures show consistent performance gains (up to 3.1% in Average Mean Class Accuracy) and reduced forgetting, with only 6% computational overhead. These results highlight our approach’s potential for privacy-preserving, efficient CL in sensitive domains like healthcare, offering a promising direction for developing adaptive AI systems that can learn continuously while respecting data privacy constraints., This work was partially supported by Lenovo and Intel as part of the Lenovo AI Innovators University Research program, by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreements PID2019-107255GB-C22 and PID2021-126248OBI00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE, and by the Generalitat de Catalunya under contract 2021-SGR-00478., Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

On the relation between open project-based learning in undergraduate computer science education and contemporary technological trends

  • Tous Liesa, Rubén
  • Freitag, Fèlix
  • Berral García, Josep Lluís
Amidst rapid and constant technological change, keeping IT higher education curricula up to date is becoming increasingly challenging. For a decade, the course”Project on Information Technologies” within the undergraduate computer science studies offered by a major technical university has been pursuing an effort of continuous curriculum adaptation and active learning practices based on an open project-based learning (PBL) methodology. This article researches the implications of employing an open-ended PBL approach, with a specific focus on the alignment of acquired skills with the trends in the professional landscape. Our analysis has identified a strong correlation between the technologies utilized in the projects and the contemporary technological trends in the areas of global technological focus, programming languages, server-side technologies, database management systems, and DevOps-related tools. For the study, we analyzed empirical data gathered from over 100 projects involving more than 400 students who enrolled in this reference course, belonging to the last year of the IT higher education programme in the last 10 years. The results suggest the open project-based design as a teaching means in the student’s study plan for fostering the student the learning of prevailing current practical technologies., This work is partially supported by the Span-ish Ministry of Science under contracts PID2019-107255GB, PID2019-106774RB-C21, PID2021-126248OB-I00 (MCIN/AEI/10.13039/501100011033/FEDER), PDC2023-145809-I00 (PDC/AEI/10.13039/501100011033), the Recovery and Resilience Facility of the European Union, and by the SGR programme of the Catalan Government under contracts 2021-SGR-00478 and 2021-SGR-01059., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Feature engineering for agents: an adaptive cognitive architecture for interpretable ML monitoring

  • Bravo Rocca, Gusseppe Jesus
  • Liu, Peini
  • Guitart Fernández, Jordi
  • Carrillo Larco, Rodrigo M.
  • Dholakia, Ajay
  • Ellison, David
Monitoring Machine Learning (ML) models in production environments is crucial, yet traditional approaches often yield verbose, low-interpretability outputs that hinder effective decision-making. We propose a cognitive architecture for ML monitoring that applies feature engineering principles to agents based on Large Language Models (LLMs), significantly enhancing the interpretability of monitoring outputs. Central to our approach is a Decision Procedure module that simulates feature engineering through three key steps: Refactor, Break Down, and Compile. The Refactor step improves data representation to better capture feature semantics, allowing the LLM to focus on salient aspects of the monitoring data while reducing noise and irrelevant information. Break Down decomposes complex information for detailed analysis, and Compile integrates sub-insights into clear, interpretable outputs. This process leads to a more deterministic planning approach, reducing dependence on LLM-generated planning, which can sometimes be inconsistent and overly general. The combination of feature engineering-driven planning and selective LLM utilization results in a robust decision support system, capable of providing highly interpretable and actionable insights. Experiments using multiple LLMs demonstrate the efficacy of our approach, achieving significantly higher accuracy compared to various baselines across several domains., This work was partially supported by Lenovo and Intel® as part of the Lenovo AI Innovators University Research program, by Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under contracts PID2019- 107255GB-C22 and PID2021-126248OB-I00, and by the Generalitat de Catalunya (AGAUR) under contract 2021-SGR-00478., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Inverse geo-electromagnetic modeling: a systematic review and bibliometric assessment

  • Castillo Reyes, Octavio
  • Jiménez Andrade, José Luis
  • Dehiya, Rahul
  • Iturraràn Viveros, Ursula
Inverse electromagnetic (EM) modeling plays a pivotal role in subsurface exploration, enabling the characterization of the Earth’s electrical properties for various applications, including resource exploration, environmental monitoring, and geohazard assessment. Despite significant advancements in the field, the EM inverse problem remains inherently challenging due to its ill-posed and nonlinear nature. A diverse range of methodologies, including deterministic, non-deterministic, and machine learning-based (ML-based) approaches, have been proposed to address these challenges. However, there is a lack of a comprehensive synthesis that integrates both the theoretical evolution of these methods and their bibliometric performance. This paper addresses this gap by combining a systematic review of modern computational methodologies with a bibliometric assessment of the scientific literature on inverse EM modeling. The systematic review critically evaluates key computational approaches, examining their theoretical foundations, practical applications, and limitations, while the bibliometric assessment provides a quantitative assessment of scientific productivity, trends, and contributions from different nations. This integrated perspective offers a unified overview of the field, identifies emerging research directions, and highlights the state-of-the-art in inverse EM modeling. The findings provide valuable insights for researchers, practitioners, and policymakers, guiding future advancements and fostering interdisciplinary collaboration., The work of OC have received funding from the MCIN/AEI/10.13039/501100011033 (Spain) and from the European Union NextGenerationEU/PRTR under the project GEOTHERPAL-EM_TED2021-131882B-C42 and -C41. OC has also been partially financed by Generalitat de Catalunya (AGAUR) under grant agreement 2021-SGR-00478. JJA has received support form DGAPA-UNAM IN310325. UI-V was partially supported by JST SATREPS Japan Grant Number JPMJSA2310; DGAPA-UNAM project numbers: IN111823, IN107720 and CONAHCYT México under Ciencia de Frontera Project Number: 6655. Finally, this work has been partially financed by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE. Authors thanks to Josep Ll. Berral (UPC) and the CROMAI team (UPC) for their support on this research., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

MScheduler: leveraging spot instances for high-performance reservoir simulation in the cloud

  • Albuquerque Portella, Felipe
  • Estrela, Paulo J.B.
  • Malini, Renzo Q.
  • Teylo, Luan
  • Berral García, Josep Lluís
  • Drummond, Lúcia M.A.
Petroleum reservoir simulation uses computer models to predict fluid flow in porous media, aiding to forecast oil production. Engineers execute numerous simulations with different geological realizations to refine the accuracy of the model. These experiments require considerable computational resources, which are not always available within the on-premises infrastructure. Commercial public cloud platforms can offer many advantages, such as virtually unlimited scalability and payper-use pricing. This paper introduces MSCHEDULER, a meta scheduler framework for reservoir simulations at Petrobras, a Brazilian energy company. It efficiently executes jobs in the cloud, utilizing spot Virtual Machines (VMs) to reduce costs and ensure job completion even with VM termination. Contributions include a novel methodology for reservoir simulation checkpointing, a cost-based scheduler, and an analysis of the strategy using real production jobs from Petrobras., This work was funded by Petroleo Brasileiro S.A. – Petrobras, by Project Universal/CNPq no 404087/2021-3 and CNE/FAPERJ no E-26/201.012/2022(271103). Also by Spanish Ministry of Science (MICINN, AEI, ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE, and Generalitat de Catalunya (AGAUR) 2021-SGR-00478., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Integrating reliability into intent-driven orchestration on kubernetes-based edge nodes

  • Berral García, Josep Lluís
  • Aguilera Luzón, David
  • Liu, Peini
  • Nou Castell, Ramon
  • Serrano, María A.
  • Antonopoulos, Angelos
  • Santaella Sánchez, Javier
  • Divan Koller, Mario José
Placing workloads across the Edge and Cloud can be performed through containerization. However, conditions in Edge nodes are very different from Cloud, as environmental factors such as temperature, humidity, voltage provisioning or dust, heavily affect execution performance and device health. Reliability is an important factor when deciding to deploy such load onto Edge devices, indicating their capability to achieve a desired Quality of Service (QoS). For this, research on Edge computing must focus on how to monitor, estimate and manage devices, in a distributed, autonomous and reliable manner. Our current efforts on performance analysis for devices under "wild conditions" are moving towards integrating reliability into orchestrator systems. Here we present our vision and roadmap for expanding Cloud orchestration towards the Edge with technologies capable of providing knowledge about node environmental conditions and mitigate its impact. Through Out-Of-Band telemetry, we can retrieve temperature and power consumption variables from node components, indicating its health and estimating its reliability given external stress factors. In particular, using intent-based orchestration for containerized platforms, such factors can be used for enforcing reliability as a key-performance indicator. The current work in progress focuses on industrial and commercial scenarios, e.g., Edge computing for urban mobility, with road-side nodes performing AI-based Video-Analytics, exposed to uncontrolled weather conditions. The principal objective is to achieve an Edge network orchestration that takes into account node health in an automatic manner for reducing operational costs such as energy consumption, device repair and replacement, while maintaining QoS in the Edge., This work is financed by the INTEL UFunding #14780, the EU-HORIZON and MSCA programmes under GA.101092646 and GA.101086248, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

A data-driven ML approach for maximizing performance in LLM-adapter serving

  • Agulló López, Ferran
  • Oliveras Torra, Joan
  • Wang, Chen
  • Gutiérrez Torre, Alberto
  • Tardieu, Olivier
  • Youssef, Alaa
  • Torres Viñals, Jordi
  • Berral García, Josep Lluís
With the rapid adoption of Large Language Models (LLMs), LLM-adapters have become increasingly common, providing lightweight specialization of large-scale models. Serving hundreds or thousands of these adapters on a single GPU allows request aggregation, increasing throughput, but may also cause request starvation if GPU memory limits are exceeded. To address this issue, this study focuses on determining the joint configuration of concurrent and parallel adapters that maximizes GPU throughput without inducing starvation, given heterogeneous adapter and traffic properties. We propose a data-driven ML approach leveraging interpretable models to tackle this caching problem and introduce the first Digital Twin capable of reproducing an LLM-adapter serving system, enabling efficient training data generation. Experiments with the vLLM framework and LoRA adapters show that the Digital Twin reproduces throughput within 5.1% of real results, while the ML approach predicts optimal numbers of concurrent and parallel adapters with an error of at most 7.2% under heterogeneous, real-world workloads., This work has been partially financed by the EU-HORIZON MSCA programme under grant agreement EU-HORIZON MSCAGA.101086248. Also, it has been partially financed by Generalitat de Catalunya (AGAUR)under grant agreement 2021-SGR-00478, by Severo Ochoa Center of Excellence CEX-2021-001148-S-20-3, and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/ FEDER, UE., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Scalable energy-aware VM allocation on cloud data centers through mathematical programming models

  • Meroni, Roberto
  • Guitart Fernández, Jordi
Cloud data centers are becoming indispensable pillars of modern society, driving AI innovation, global connectivity, and data-driven advancements. As their size and complexity grow, so does the urgency for sustainable and efficient solutions to address operational and environmental challenges. The Virtual Machine (VM) allocation problem lies at the heart of these challenges, directly impacting energy consumption, scalability, and cost-effectiveness. While heuristics are traditionally favored for their fast execution times, they fail to adequately address the complexities of heterogeneous environments and the increasing need for energy-aware solutions. In this work, we redefine the potential of mathematical programming models — traditionally considered impractical due to scalability limitations — by defining a comprehensive VM allocation strategy that embeds the models into scalable algorithms that distribute computational workloads and exploit solver capabilities. This approach achieves linear scalability — an unprecedented milestone for mathematical programming — allowing us to integrate detailed and heterogeneous aspects of the VM allocation problem. The resulting algorithms dramatically outperform state-of-the-art heuristics and metaheuristics in both scalability and solution quality, delivering an average 16% increase in Net Profit, a 54% reduction in Total Energy Consumption, and a more-than-double improvement in Energy Efficiency. Designed to meet the evolving demands of modern Cloud data centers, our algorithms scale efficiently to manage growing workloads, adapt to heterogeneity, and comply with sustainability and regulatory requirements by prioritizing energy efficiency, facilitating the transition to next-generation Cloud environments., This research was partially supported by the EU-HORIZON programme under grant agreement EU-HORIZON GA.101092646, by the Spanish Ministry of Science and the Research State Agency (MICIU/AEI/ 10.13039/501100011033) and by European Regional Development Funds (ERDF/FEDER) under contract PID2021-126248OB-I00, and by the Generalitat de Catalunya (AGAUR) under contract 2021-SGR-00478., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Data-Connector: an agent-based framework for autonomous ML-based smart management in cloud-edge continuum

  • Liu, Peini
  • Oliveras Torra, Joan
  • Palacín Marfil, Marc
  • Guitart Fernández, Jordi
  • Berral García, Josep Lluís
  • Nou Castell, Ramon
Machine Learning (ML) is becoming pervasive and integrated into different kinds of intelligent applications, and the collaborative Cloud-Edge continuum has been introduced as an emerging trend to support their adoption into use cases. However, managing these ML applications in the CloudEdge continuum is challenging due to the ML application's dynamic resource usage with different user loads and Cloud and Edge's dynamic resource availability. We envision machine learning methods that can be used for smart management in this dynamic environment, but how to deploy and utilize them for the adaptation scenario in Cloud-Edge continuum is unknown. This paper proposes an agent-based framework to enable autonomous smart management mechanisms that can be broadly enabled in diverse adaptation scenarios. The agent acts as a data-connector1 1https://github.com/bsc-scanflow/data-connector, connecting different sources of data, utilizing ML models for decision-making and triggering adaptations in Cloud-edge platforms. The case study shows the feasibility of our proposed data-connector for smart migration of an ML workload in the Cloud-edge continuum. The result shows that the smart migration-enabled Cloud-edge scenario has 11.9% ML application prediction time better than the Cloud scenario without migration. Moreover, with minimal customization, the data connector agent can be adapted for more use cases., This work is financed by the EU-HORIZON programme under grant agreements EU-HORIZON GA.101092646, EU-HORIZON MSCA GA.101086248, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

FRIDA: Free-rider detection using privacy attacks

  • Garcia Recasens, Pol
  • Horváth, Ádám
  • Gutiérrez Torre, Alberto
  • Torres Viñals, Jordi
  • Berral García, Josep Lluís
  • Pejó, Balázs
Federated learning is increasingly popular as it enables multiple parties with limited datasets and resources to train a machine learning model collaboratively. However, similar to other collaborative systems, federated learning is vulnerable to free-riders — participants who benefit from the global model without contributing. Free-riders compromise the integrity of the learning process and slow down the convergence of the global model, resulting in increased costs for honest participants. To address this challenge, we propose FRIDA: free-rider detection using privacy attacks. Instead of focusing on implicit effects of free-riding, FRIDA utilizes membership and property inference attacks to directly infer evidence of genuine client training. Our extensive evaluation demonstrates that FRIDA is effective across a wide range of scenarios., Project no. 145832, implemented with the support provided by the Ministry of Innovation and Technology from the NRDI Fund, financed under the PD_23 funding scheme. Also, partially financed by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI), and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/501100011033/FEDER, UE, and Generalitat de Catalunya (AGAUR) under grant 2021-SGR-00478. Lastly, also funded by the European Union (Grant Agreement Nr. 101095717, SECURED Project)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

In-context bias propagation in LLM-based tabular data generation

  • Garcia Recasens, Pol
  • Gutiérrez Torre, Alberto
  • Torres Viñals, Jordi
  • Berral García, Josep Lluís
  • Halimi, Anisa
  • Fraser, Kieran
Large Language Models (LLMs) are increasingly used for synthetic tabular data generation through in-context learning (ICL), offering a practical solution for data augmentation in data scarce scenarios. While prior work has shown the potential of LLMs to improve downstream task performance through augmenting underrepresented groups, these benefits often assume access to a subset of unbiased in-context examples, representative of the real dataset. In real-world settings, however, data is frequently noisy and demographically skewed. In this paper, we systematically study how statistical biases within in-context examples propagate to the distribution of synthetic tabular data, showing that even mild in-context biases lead to global statistical distortions. We further introduce an adversarial scenario where a malicious contributor can inject bias into the synthetic dataset via a subset of in-context examples, ultimately compromising the fairness of downstream classifiers for a targeted and protected subgroup. Finally, we evaluate mitigation strategies based on preprocessing in-context examples, demonstrating that while such interventions can attenuate disparity, the inherent sensitivity of LLMs to adversarial prompts remains a persistent challenge. Our findings highlight a critical new vulnerability in LLM-based data generation pipelines within sensitive domains, This work has been partially financed by grant agreement EU-HORIZON GA.101095717 and by grant agreement EU-HORIZON MSCA GA.101086248. Also, it has been partially financed by Generalitat de Catalunya (AGAUR) under grant agreement 2021-SGR-00478, by Severo Ochoa Center of Excellence CEX-2021-001148-S20-3, and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/ FEDER, UE. Kieran Fraser and Anisa Halimi were partly supported by the Innovative Health Initiative Joint Undertaking (IHI JU) under grant agreement No. 101172997– SEARCH., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Mobility usecase: intelligent service migration in cloud-edge continuum

  • Liu, Peini
  • Oliveras Torra, Joan
  • Palacín Marfil, Marc
  • Dalgitsis, Michail
  • Serrano, María A.
  • Datsika, Eftychia
  • Antonopoulos, Angelos
  • Santaella Sánchez, Javier
  • Guitart Fernández, Jordi
  • Berral García, Josep Lluís
  • Nou Castell, Ramon
As industries increasingly embrace digital and intelligent transformation, enterprises face significant challenges in the containerization upgrades for their Artificial Intelligence(AI) applications and dynamic service migration and management in Cloud-Edge continuum(CEC). This paper presents CloudSkin, an innovative platform designed to realize streamlined, seamless and intelligent service migration in Cloud-Edge Continuum by integrating advanced containerization techniques and AI-driven orchestration capabilities. Our approach, leveraging intelligent algorithms for service migration, can seamlessly transit services between cloud and edge environments, ensuring optimised resource allocation and reducing service latency to assure quality of service(QoS). CloudSkin has been enabled in a Mobility Usecase, empowering Cellnex businesses undergoing digital transformation to achieve higher operational efficiency. The experimental results show that compared to traditional reactive service migration, using intelligent proactive service migration can provide better migration detection, improving F1-Score up to 23.5%, and reducing 28.9% the service running time where the service latency violates SLA., This work is financed by the EU-HORIZON programme under grant agreements EU-HORIZON GA.101092646, EU-HORIZON MSCA GA.101086248, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

SynthVal: A framework for validating synthetic medical images

  • Guidotti, Dario
  • Pandolfo, Laura
  • Gutiérrez Torre, Alberto
  • López Rúbio, Omar
  • Pulina, Luca
Synthetic data is increasingly used in medical imaging to overcome data scarcity and privacy constraints. However, assessing the fidelity of synthetic images remains a critical challenge for ensuring their safe and effective use in clinical and AI applications. We present SynthVal, a Python-based framework for validating the quality of synthetic medical images through statistical comparisons in deep feature space. SynthVal extracts semantic image embeddings using transformer-based models and computes similarity metrics – including Fréchet Distance, Wasserstein Distance, and Kullback-Leibler Divergence – between real and synthetic data distributions. The framework is designed for modularity, scalability, and ease of integration into existing workflows via pip installation. We evaluate SynthVal using real images from the CSAW-CC dataset, and synthetic images produced by a model developed by the Barcelona Supercomputing Center. Our experiments systematically benchmark the influence of different feature extraction models and similarity metrics, providing practical insights for selecting validation strategies in medical image synthesis. SynthVal offers a reproducible and extensible solution for quality control in synthetic data pipelines., The work of Dario Guidotti, Laura Pandolfo, and Luca Pulina was supported by EU Project SECURED, ‘‘Scaling Up Secure Processing, Anonymization and Generation of Health Data for EU Cross-Border Collaborative Research and Innovation,’’ under Agreement 101095717. The work of Alberto Gutierrez-Torre and Omar Lopez-Rubio was supported by SECURED under Agreement 101095717; in part by Spanish Ministry of Science (MICINN), the State Research Agency (AEI), and European Regional Development Funds (ERDF/FEDER) under Grant PID2021-126248OB-I00; in part by MCIN/AEI/10.13039/501100011033/FEDER, UE; and in part by the Generalitat de Catalunya (AGAUR) under Grant 2021-SGR-00478., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

CloudSkin: ML-based smart management for the cloud-edge continuum

  • Liu, Peini
  • Nestorov, Anna Maria
  • Palacín Marfil, Marc
  • Nou Castell, Ramon
  • Guitart Fernández, Jordi
  • Berral García, Josep Lluís
The CloudSkin project embraces ML-based autonomous management technologies, introducing the Learning Plane (LP), which provides services and methods to embed intelligence in Cloud-Edge Continuum management layers. By leveraging AI, the continuum can achieve user demands for resource, privacy, resilience, and energy efficiency requirements, in an adaptive way. As a first Proof-of-Concept, we envision a smart orchestrator to drive a 5G-powered automotive usecase, focusing on a mobility scenario where the LP optimises resources for AI data and applications, on a transversal Edge environment., This work is financed by the EU-HORIZON programme under grant agreements EU-HORIZON GA.101092646, EU-HORIZON MSCA GA.101086248, EU-HORIZON GA.101092644, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

A reliability score for video-analytics edge-IoT devices in urban environments

  • Garcia Boris, Marçal
  • Oliveras Torra, Joan
  • Aguilera Luzón, David
  • Liu, Peini
  • Divan Koller, Mario José
  • Berral García, Josep Lluís
Performing video-analytics in Edge and IoT devices towards urban mobility allows computing near-data, providing fast and autonomous management from streets and roads. Thanks to advances in artificial intelligence methods, real-time classification of camera-provided image feeds can be performed in low-power devices to be deployed next to urban signaling and city services. However, devices deployed “in the wild” are affected by environmental factors such as temperature, either ambient or retained by its container, humidity or voltage changes, coming from sensorized urban furniture. Deciding where to deploy video-analytics workload requires a minimal device performance reliability, assuring that load can be processed in-place, before moving it towards the Fog/Cloud or other nearby devices. Here we present a simplistic factorization of a reliability Score to be quickly computed in Edge nodes, towards orchestrating workload according to the node surrounding environment. The score takes into account ambient temperature and humidity, also received voltage. The scoring is evaluated performing video-analytics workloads on real devices under physical stress, observing the performance degradation related to the external and internal factors applied onto the device. From the study, we observe how the different factors affect the functioning mode and quality of service, aside of indicating an estimation of the reliability of the urban-placed devices., This work is financed by the INTEL UFunding #14780, the EU-HORIZON and MSCA programmes under GA.101092646 and GA.101086248, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Embedded scaffolding for teaching and assessing inquiry-based hands-on laboratory on distributed systems

  • Guitart Fernández, Jordi
Context Information Technology education must cultivate proficiency on distributed systems, including strong hands-on laboratory skills, to meet the needs of the society and the industry. Given the complexity of distributed systems, any successful methodology to teach them to novice students must be scaffolded appropriately to ensure that the students acquire the required degree of expertise. Objective We propose a comprehensive scaffolding approach for inquiry-based hands-on laboratory on a distributed systems course, which guides not only the learning process, but also its assessment. The approach is based mainly on embedded scaffolds, namely explicit coding and experimental milestones and open questions with predefined grades, but also features contingent scaffolds provided by the teacher when additional assistance is needed. Method We apply the methodology in the context of the subject ‘Distributed Network Systems’ offered by our university. We compare the students' performance during three academic courses using the proposed methodology with respect to the three previous courses that were still using the former methodology. We use both visual representations and planned Analysis of Variance (ANOVA) tests to verify our hypothesis defined as a complex contrast. Findings We find that there is a statistically significant improvement in the students' performance when using the new methodology, both in their grades of the assignments (F(1, 75.364) = 17.770, p = 6.85*10^-5) and, more importantly, also in their grades of the exam questions about the practicals (F(1, 123.186) = 13.285, p = 3.93*10^-4). Implications Our results encourage other instructors to incorporate embedded scaffolds for teaching and assessing their hands-on laboratories on distributed systems., This research was partially supported by the Agencia Estatal de Investigación under contracts PID2019-107255GB-C22 and PID2021-126248OB-I00 and by the Generalitat de Catalunya under contract 2021-SGR-00478., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Towards Pareto optimal throughput in small language model serving

  • Garcia Recasens, Pol
  • Zhu, Yue
  • Wang, Chen
  • Lee, Eun Kyung
  • Tardieu, Olivier
  • Youssef, Alaa
  • Torres Viñals, Jordi
  • Berral García, Josep Lluís
Large language models (LLMs) have revolutionized the state-of-the-art of many different natural language processing tasks. Although serving LLMs is computationally and memory demanding, the rise of Small Language Models (SLMs) offers new opportunities for resource-constrained users, who now are able to serve small models with cutting-edge performance. In this paper, we present a set of experiments designed to benchmark SLM inference at performance and energy levels. Our analysis provides a new perspective in serving, highlighting that the small memory footprint of SLMs allows for reaching the Pareto-optimal throughput within the resource capacity of a single accelerator. In this regard, we present an initial set of findings demonstrating how model replication can effectively improve resource utilization for serving SLMs., This work has been partially financed by grant agreement EUHORIZON GA.101095717 and by the EU-HORIZON MSCA programme under grant agreement EU-HORIZON MSCA GA.101086248. Also, it has been partially financed by Generalitat de Catalunya (AGAUR) under grant agreement 2021- SGR-00478, and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/ 10.13039/ 501100011033/ FEDER, UE., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Enhancing the output of time series forecasting algorithms for cloud resource provisioning

  • Agulló López, Ferran
  • Gutiérrez Torre, Alberto
  • Torres Viñals, Jordi
  • Berral García, Josep Lluís
Forecasting the resource consumption of workloads is a frequent approach in the cloud provisioning field. Ideally, such predictions allow obtaining a more accurate scheduling and management of resources in a computing cluster. However, the current approaches fail to properly forecast the future consumption in areas where sudden increases of consumption are present, i.e., spikes. Even, commonly employed metrics lack the ability to properly evaluate sharp behaviours in the traces. This may generate resource starvation problems in the running workloads and decreases the Quality of Service (QoS) provided to external users. To address this issue, we propose two strategies that modify the outputs of forecasting algorithms without changing the algorithms’ internals. The new outputs considerably enhance the prediction of sudden increases, duplicating the F1 score metric in average for all tested algorithms. This improvement in the handling of spikes comes with an increased over-provision of resources. Nevertheless, the proposed strategies give the user an easy way to control this trade-off between predicting spikes and the amount of over-provision. The user can decide which is the right balance that better fits the requirements of its specific scenario. Furthermore, we propose a new evaluation methodology that better assesses the behaviour of forecasting algorithms in cloud traces, especially focused on the performance around increases of consumption, and we give insights on the reasons behind the predictions of the algorithms with the application of explainability techniques. The code repository of this work can be accessed through GitHub at this link https://github.com/FerranAgulloLopez/ResourceForecasting., This work has been supported by the EU’s Horizon research and innovation programme under grant agreements HORIZON GA.101092646 (CloudSkin), HORIZON MSCA GA.101086248 (CloudStars), and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreements PID-2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033, UE (DALEST), Severo Ochoa Center of Excellence CEX-2021-001148-S-20-3 and the Generalitat de Catalunya (AGAUR), Spain 2021-SGR-00478 (CROMAI)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Mind the memory gap: unveiling GPU bottlenecks in large-batch LLM inference

  • Garcia Recasens, Pol
  • Agulló López, Ferran
  • Zhu, Yue
  • Wang, Changyang
  • Lee, Eun Kyung
  • Tardieu, Olivier
  • Torres Tomás, Juan José
  • Berral García, Josep Lluís
Large language models have been widely adopted across different tasks, but their auto-regressive generation nature often leads to inefficient resource utilization during inference. While batching is commonly used to increase throughput, per-formance gains plateau beyond a certain batch size, especially with smaller models, a phenomenon that existing literature typically explains as a shift to the compute-bound regime. In this paper, through an in-depth GPU-level analysis, we reveal that large-batch inference remains memory-bound, with most GPU compute capabilities underutilized due to DRAM bandwidth saturation as the primary bottleneck. To address this, we propose a Batching Configuration Advisor (BCA) that optimizes memory allocation, reducing GPU memory requirements with minimal impact on throughput. The freed memory and underutilized GPU compute capabilities can then be leveraged by concurrent workloads. Specifically, we use model replication to improve serving throughput and GPU utilization. Our findings challenge conventional assumptions about LLM inference, offering new in-sights and practical strategies for improving resource utilization, particularly for smaller language models., This work has been partially financed by grant agreement EU-HORIZON GA.101095717 and by the EU-HORIZON MSCA programme under grant agreement EU-HORIZON MSCA GA.101086248. Also, it has been partially financed by Generalitat de Catalunya (AGAUR) under grant agreement 2021-SGR-00478, by Severo Ochoa Center of Excellence CEX-2021-001148-S-20-3, and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OBI00, MCIN/AEI/10.13039/ 501100011033/ FEDER, UE., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Time-quality tradeoff of MuseHash query processing performance

  • Pegia, Maria
  • Agulló López, Ferran
  • Moumtzidou, Anastasia
  • Gutiérrez Torre, Alberto
  • Jónsson, Björn Þór
  • Berral García, Josep Lluís
  • Gialampoukidis, Ilias
  • Vrochidis, Stefanos
  • Kompatsiaris, Ioannis
Nowadays, large quantities of multimedia data are generated by various applications on smartphones, drones and other devices. Facilitating retrieval from these multimedia collections requires (a) effective media representation and (b) efficient indexing and query processing approaches. Recently, the MuseHash approach was proposed, which can effectively represent a variety of modalities, improving on previous hashing-based approaches. However, the interaction of the MuseHash approach with existing indexing and query processing approaches has not been considered. This paper provides the first systematic evaluation of the time-quality tradeoff that arises when MuseHash media representation is combined with state-of-the-art approximate nearest-neighbour indexes along multi-core and GPU processing., The work reported here was supported by the EU’s Horizon 2020 research and innovation programme under grant agreements H2020-101070250 CALLISTO, H2020-101070262 WATERVERSE, and H2020-101080090 ALLIES, and by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreements PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE, Severo Ochoa Center of Excellence CEX2021-001148-S-20-3 and the Generalitat de Catalunya (AGAUR) 2021-SGR-00478., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Dexter: a performance-cost efficient resource allocation manager for serverless data analytics

  • Nestorov, Anna Maria
  • Marrón Vida, Diego
  • Gutiérrez Torre, Alberto
  • Wang, Chen
  • Misale, Claudia
  • Youssef, Alaa
  • Carrera Pérez, David
  • Berral García, Josep Lluís
Leveraging serverless platforms for the efficient execution of distributed data analytics frameworks, such as Apache Spark [ 3], has gained substantial interest since early 2022. The elasticity, free-of-management, and on-demand scalability of serverless have motivated the effort in deploying distributed data analytics applications to serverless platforms. However, effectively auto-scaling resources for such complex workloads so that we can fully benefit from the resource elasticity of serverless remains challenging. Mis-configuration can result in severe performance and cost issues arising from resource under- and over-provisioning. In this paper, we present Dexter, a robust resource allocation manager dynamically allocating resources at a fine-grained level to guarantee performance-cost efficiency (optimizing total runtime cost). Dexter is novel in combining predictive and reactive strategies that fully leverage the elasticity of serverless to enhance the performance-cost efficiency for workflow executions. Unlike blackbox ML models, Dexter quickly reaches a sufficiently good solution, prioritizing simplicity, generality, and ease of understanding. Our experimental evaluation shows that, compared with the default serverless Spark resource allocation that dynamically requests exponentially more executors to accommodate pending tasks, our solution achieves a cost reduction of up to 4.65×, while improving performance-cost efficiency up to 3.50×. Dexter also enables a substantial resource saving, demanding up to 5.75× fewer resources., This work is financed by the EU-HORIZON programme under grant agreements EU-HORIZON GA.101092646, EU-HORIZON MSCA GA.101086248, by Generalitat de Catalunya (AGAUR) GA.2021-SGR-00478, and the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) PID2021-126248OB-I00, MCIN/AEI/10.13039/ 501100011033/FEDER, UE., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

HealthMesh: An architectural framework for federated healthcare data management

  • Bisquert Parés, Aniol
  • Hmimou Ham Man, Achraf
  • Berral García, Josep Lluís
  • Gutiérrez Torre, Alberto
  • Romero Moral, Óscar
Recently, significant milestones have been achieved in the field of healthcare data analysis. However, alongside these accomplishments, substantial data-related challenges have emerged in the domain of big data management. Modern healthcare projects are no more dealing with a single data repository but many heterogeneous ones and must overcome data variety, privacy and governance issues. Yet, current solutions face a privacy-decentralization trade-off. To address this dual challenge, we introduce HealthMesh, a novel layered architectural framework based on the Data Mesh principles, providing a domaindecentralised paradigm. In addition, the framework incorporates a Semantic Data Model which establishes robust governance, enables interoperability and guarantees policy compliance for all the data assets. To demonstrate the capabilities of the proposed approach, we provide an illustrative example inspired by the use case of the INCISIVE project for breast cancer analytics. Overall, this work makes a significant contribution on collecting key challenges, identifying actors and providing a set of components and guidelines for establishing a holistic framework for the complex field of healthcare data management., The work reported here was supported by the EU-H2020 programme under GA.952179 INCISIVE, Horizon Europe Programme under GA.101095717 (SECURED) and GA.101135513 (CYCLOPS), the Spanish Research State Agency (MICINN/AEI, ERDF/FEDER) under GA.MCIN/AEI/10.13039/501100011033/FEDER (UE DALEST), the Spanish Ministerio de Ciencia e Innovación under project PID2020-117191RB-I00 / AEI/10.13039/501100011033 (DOGO4ML), and the Generalitat de Catalunya (AGAUR) 2021-SGR-00478 (CROMAI)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Towards generalizable Federated Learning in medical imaging: a real-world case study on mammography data

  • Tzortzis, Ioannis N.
  • Gutiérrez Torre, Alberto
  • Sykiotis, Stavros
  • Agulló López, Ferran
  • Bakalos, Nikolaos
  • Doulamis, Anastasios
  • Doulamis, Nikolaos
  • Berral García, Josep Lluís
Federated Learning has been rapidly gaining in popularity in medical applications, due to the increased privacy offered, since medical data doesn't need to leave the hospitals' premises for AI model training. However, a direct translation of a classic experiment to a federated one is not always straightforward. In this work, we delve into the intricacies of federated learning for a breast cancer classification tool. We compare classic model training with a federated variant, and highlight the adaptations that need to be taken care of to ensure the equivalence between the two. Specifically, we introduce the Breast Area Detection tool as an essential component of the pre-processing pipeline to enhance the robustness of Federated Learning by offering data harmonization. On top of that, we present an end-to-end Federated Learning framework that is effective for real-world data and scenarios. Among the three real-world hospitals involved in the experimental procedure, the proposed framework significantly improves performance at the first hospital, providing consistent results similar to those achieved in the classic approach. Experimental results demonstrate that the interventions introduced improved model performance by approximately 35%, aligning federated learning and centralized model performance., This paper is funded by the EU funded projects SECURED “Scaling Up Secure Processing, Anonymization And Generation Of Health Data For EU Cross Border Collaborative Research And Innovation” with grant agreement no. 101095717 and INCISIVE “A multimodal AI-based toolbox and an interoperable health imaging repository for the empowerment of imaging analysis related to the diagnosis, prediction and follow-up of cancer” with grant agreement no. 952179. This paper has been partially financed by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI) and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, Severo Ochoa Center of Excellence CEX-2021-001148-S-20-3, 2021- SGR-00478, UE, also Generalitat de Catalunya (AGAUR) under grant agreement 2021-SGR-00478., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Exhaustive variant interaction analysis using multifactor dimensionality reduction

  • Gómez Sánchez, Gonzalo
  • Alonso Parrilla, Lorena
  • Pérez Elena, Miguel Ángel
  • Morán, Ignasi
  • Torrents Arenales, David
  • Berral García, Josep Lluís
One of the main goals of human genetics is to understand the connections between genomic variation and the predisposition to develop a complex disorder. These disease–variant associations are usually studied in a single independent manner, disregarding the possible effect derived from the interaction between genomic variants. In particular, in a background of complex diseases, these interactions can be directly linked to the disorder and may play an important role in disease development. Although their study has been suggested to help complete the understanding of the genetic bases of complex diseases, this still represents a big challenge due to large computing demands. Here, we take advantage of high-performance computing technologies to tackle this problem by using a combination of machine learning methods and statistical approaches. As a result, we created a containerized framework that uses multifactor dimensionality reduction (MDR) to detect pairs of variants associated with type 2 diabetes (T2D). This methodology was tested on the Northwestern University NUgene project cohort using a dataset of 1,883,192 variant pairs with a certain degree of association with T2D. Out of the pairs studied, we identified 104 significant pairs: two of which exhibit a potential functional relationship with T2D. These results place the proposed MDR method as a valid, efficient, and portable solution to study variant interaction in real reduced genomic datasets., This work was partially financed by the European Commission (EU-HORIZON NEARDATA GA.101092644) and by the Universitat Politècnica de Catalunya (45-FPIUPC2018); it was also partially financed by Generalitat de Catalunya (AGAUR) under grant agreement 2021-SGR-00478; it was also partially financed by the Spanish Ministry of Science (MICINN), the Research State Agency (AEI), and European Regional Development Funds (ERDF/FEDER) under grant agreement PID2021-126248OB-I00, MCIN/AEI/10.13039/501100011033/FEDER, UE., Peer Reviewed, Postprint (published version)