Pasar al contenido principal

APRENDIZAJE PROFUNDO ETICO

PID2021-128045OA-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2021
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDADE DA CORUÑA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 11
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

FedHEONN: Federated and homomorphically encrypted learning method for one-layer neural networks

  • Fontenla-Romero, Óscar
  • Guijarro-Berdiñas, Bertha
  • Hernández-Pereira, Elena
  • Pérez-Sánchez, Beatriz
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Federated learning (FL) is a distributed approach to developing collaborative learning models from decentralized data. This is relevant to many real applications, such as in the field of the Internet of Things, since the models can be used in edge computing devices. FL approaches are motivated by and designed to protect privacy, a highly relevant issue given current data protection regulations. Although FL methods are privacy-preserving by design, recently published papers show that privacy leaks do occur, caused by attacks designed to extract private data from information interchanged during learning. In this work, we present an FL method based on a neural network without hidden layers that incorporates homomorphic encryption (HE) to enhance robustness against the above-mentioned attacks. Unlike traditional FL methods that require multiple rounds of training for convergence, our method obtains the collaborative global model in a single training round, yielding an effective and efficient model that simplifies management of the FL training process. In addition, since our method includes HE, it is also robust against model inversion attacks. In experiments with big data sets and a large number of clients in a federated scenario, we demonstrate that use of HE does not affect the accuracy of the model, whose results are competitive with state-of-the-art machine learning models. We also show that behavior in terms of accuracy is the same for identically and non-identically distributed data scenarios., This work has been supported by the grant Machine Learning on the Edge - Ayudas Fundación BBVA a Equipos de Investigación Científica 2019; the National Plan for Scientific and Technical Research and Innovation of the Spanish Government (Grants PID2019-109238GB-C2 and PID2021-128045OA-I00); and by the Xunta de Galicia (ED431C 2022/44) with the European Union ERDF funds. CITIC, as a Research Center of the University System of Galicia, is funded by Consellería de Educación, Universidade e Formación Profesional of the Xunta de Galicia through the European Regional Development Fund (ERDF) and the Secretaría Xeral de Universidades (Ref. ED431G 2019/01). Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

On the Reliability of Machine Learning Models for Survival Analysis When Cure Is a Possibility

  • Ezquerro, Ana
  • Cancela, Brais
  • López-Cheda, Ana
[Abstract]: In classical survival analysis, it is assumed that all the individuals will experience the event of interest. However, if there is a proportion of subjects who will never experience the event, then a standard survival approach is not appropriate, and cure models should be considered instead. This paper deals with the problem of adapting a machine learning approach for classical survival analysis to a situation when cure (i.e., not suffering the event) is a possibility. Specifically, a brief review of cure models and recent machine learning methodologies is presented, and an adaptation of machine learning approaches to account for cured individuals is introduced. In order to validate the proposed methods, we present an extensive simulation study in which we compare the performance of the adapted machine learning algorithms with existing cure models. The results show the good behavior of the semiparametric or the nonparametric approaches, depending on the simulated scenario. The practical utility of the methodology is showcased through two real-world dataset illustrations. In the first one, the results show the gain of using the nonparametric mixture cure model approach. In the second example, the results show the poor performance of some machine learning methods for small sample sizes., This project was funded by the Xunta de Galicia (Axencia Galega de Innovación) Research projects COVID-19 presented in ISCIII IN845D 2020/26, Operational Program FEDER Galicia 2014–2020; by the Centro de Investigación de Galicia “CITIC”, funded by Xunta de Galicia and the European Union European Regional Development Fund (ERDF)-Galicia 2014–2020 Program, by grant ED431G 2019/01; and by the Spanish Ministerio de Economía y Competitividad (research projects PID2019-109238GB-C22 and PID2021-128045OA-I00). ALC was sponsored by the BEATRIZ GALINDO JUNIOR Spanish Grant from MICINN (Ministerio de Ciencia e Innovación) with code BGP18/00154. ALC was partially supported by the MICINN Grant PID2020-113578RB-I00 and partial support of Xunta de Galicia (Grupos de Referencia Competitiva ED431C-2020-14). We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research., Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431C-2020-14, Xunta de Galicia; IN845D 2020/26
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Spatial–temporal feature-based End-to-end Fourier network for 3D sign language recognition

  • Abdullahi, Sunusi Bala
  • Chamnongthai, Kosin
  • Bolón-Canedo, Verónica
  • Cancela, Brais
This is the Accepted Manuscript. This version of the article has been accepted for publication in: Expert Systems with Applications, 248, 123258. The Version of Record is available online at https://doi.org/10.1016/j.eswa.2024.123258., [Abstract]: Most dynamic sign word misclassifications are caused by redundant spatial–temporal (SPT) feature pruning that lacks language semantic and temporal dependencies. SPT feature recognition is one of the important aspects for the evaluation of the misclassification of dynamic sign words. The redundant pruning of SPT feature space influences the language model of sign confusion, model complexity, and SPT feature similarity. The purpose of this article is to develop a new multi-scale SPT feature-based dynamic sign word recognition approach via a low-cost feature selection method (FS) and End-to-end Fourier convolution neural network (EFCNN). Instead of a sensor fusion technique for obtaining frame position alignment, in the EFCNN, new 3D frame position and coordinates are determined using a pixel weighting and alignment function of the first and succeeding 25 spatial intensities of the 3D video changes across hand motion. The new spatial weight and the original spatial coordinates are fused and truncated in the Fourier domain. We generate the temporal dependence of the fused features. A feature selection known as the FS-EFCNN is introduced to select compact features with a preserved language meaning. Five state-of-the-art feature selection methods, namely Infinite FS (InFS), Relief FS, Fisher, MIM, ILFS, and ensemble FS-EFCNN were deployed to guide and optimize the learning performance of EFCNN. The experimental result analysis highlighted the improved results of the FS-EFCNN method with the best accuracy of 99.86%, 99.89%, and 90.69% on 3D American Sign Language, British Sign Language, and Greek Sign Language data sets, respectively., This research has been financially supported in part by the Spanish Ministerio de Ciencia e Innovación MCIN/AEI/10.13039/501100011033 and ”NextGenerationEU”/PRTR under Grants [PID2019-109238GB-C22; PID2021-128045OA-I00; TED2021-130599A-I00], and by the Xunta de Galicia (ED431C 2022/44) with the European Union ERDF funds. CITIC, as a Research Center of the University System of Galicia, is funded by Consellería de Educación, Universidade e Formación Profesional of the Xunta de Galicia, Spain through the European Regional Development Fund (ERDF) and the Secretaría Xeral de Universidades (Ref. ED431G 2019/01). This research is also supported by King Mongkut’s University of Technology Thonburi’s Postdoctoral Fellowship Under Research Project ID 27180., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2019/01, Thailand. King Mongkut's University of Technology Thonburi; 27180
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Sustainable Techniques to Improve Data Quality for Training Image-Based Explanatory Models for Recommender Systems

  • Paz Ruza, Jorge
  • Esteban Martínez, David
  • Alonso-Betanzos, Amparo
  • Guijarro-Berdiñas, Bertha
[Abstract]: Visual explanations based on user-uploaded images are an effective and self-contained approach to provide transparency to Recommender Systems (RS), but intrinsic limitations of data used in this explainability paradigm cause existing approaches to use bad quality training data that is highly sparse and suffers from labelling noise. Popular training enrichment approaches like model enlargement or massive data gathering are expensive and environmentally unsustainable, thus we seek to provide better visual explanations to RS aligning with the principles of Responsible AI. In this work, we research the intersection of effective and sustainable training enrichment strategies for visual-based RS explainability models by developing three novel strategies that focus on training Data Quality: 1) selection of reliable negative training examples using Positive-unlabelled Learning, 2) transform-based data augmentation, and 3) text-to-image generative-based data augmentation. The integration of these strategies in three state-of-the-art explainability models increases (5%) the performance in relevant ranking metrics of these visual-based RS explainability models without penalizing their practical long-term sustainability, as tested in multiple real-world restaurant recommendation explanation datasets, This work is funded by MICIU/AEI and ESF+ (FPU21/05783), ERDF A way of making Europe (PID2019-109238GB-C22, PID2023-147404OB-I00), ERDF/EU (PID2021-128045OA-I00), Ministry for Digital Transformation and Civil Service and ‘Next-GenerationEU’/PRTR (TSI-100925-2023-1), and Xunta de Galicia (ED431C 2022/44). CITIC is funded by “Consellería de Cultura, Educación e Universidade” through ERDF and “Secretaría Xeral de Universidades" (ED431G 2023/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

An effective and efficient green federated learning method for one-layer neural networks

  • Fontenla-Romero, Óscar
  • Guijarro-Berdiñas, Bertha
  • Hernández-Pereira, Elena
  • Pérez-Sánchez, Beatriz
Presented at: SAC '24: 39th ACM/SIGAPP Symposium on Applied Computing, Avila Spain, April 8 - 12, 2024. "This is the author's version of the work. The definitive Version of Record was published in Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing (SAC '24). Association for Computing Machinery, New York, NY, USA, 1050–1052. https://doi.org/10.1145/3605098.3636144.", [Abstract]: We present a green Federated learning method (FL), based on a neural network without hidden layers, capable of generating a global collaborative model in a single training round, unlike traditional FL methods that require multiple rounds for convergence. Moreover, the method preserves data privacy by design, a crucial aspect of current data protection regulations. Experiments with large data sets and a large number of federated clients show that the model achieves competitive accuracy results compared to state-of-the-art machine learning models. Moreover, it performs equally well in identically and non-identically distributed scenarios., This work has been supported by the National Plan for Scientific and Technical Research and Innovation of the Spanish Government (Grants PID2019-109238GB-C2 and PID2021-128045OA-I00); and by the Xunta de Galicia (ED431C 2022/44) with the European Union ERDF funds. CITIC, as a Research Center of the University System of Galicia, is funded by Consellería de Educación, Universidade e Formación Profesional of the Xunta de Galicia through the European Regional Development Fund (ERDF) and the Secretaría Xeral de Universidades (Ref. ED431G 2019/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Contrastive Learning for Explanation Ranking

  • Escarda Fernández, Miguel
  • Cancela, Brais
  • Eiras-Franco, Carlos
  • Guijarro-Berdiñas, Bertha
  • Alonso-Betanzos, Amparo
Financiado para publicación en acceso aberto: CRUE-CSIC, [Abstract]: Explainable recommendation systems enhance user trust and satisfaction by revealing the reasoning behind personalized recommendations. Approaching this as a post-hoc explanation-ranking problem over a fixed pool of candidate explanations, we propose Contrastive Learning for Explanation Ranking (CLER), a model that learns user, item, and explanation representations with a Normalized Temperature-scaled Binary Cross-Entropy (NT-BXent) loss. This function specifically applies a per-row reweighting strategy, preventing the vast number of negative examples from dominating the objective. We evaluate CLER on the Amazon, TripAdvisor, and Yelp datasets from the EXTRA benchmark. Across traditional ranking metrics, CLER achieves the strongest results among the compared baselines., This work was supported in part by MICIU/AEI/10.13039/501100011033 and ERDF, EU under Grant PID2023-147404OB-I00 and Grant PID2021-128045OA-I00; in part by the Ministry for Digital Transformation and Civil Service and Next-GenerationEU/PRTR under Grant TSI-100925-2023-1; in part by the Xunta de Galicia under Grant ED431C 2022/44; and in part by Consellería de Cultura, Educación e Universidade (ERDF Operational Programme Galicia 2021–2027) and Secretaría Xeral de Universidades under Grant ED431G2023/01., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Beyond RMSE and MAE: Introducing EAUC to Unmask Hidden Bias and Unfairness in Dyadic Regression Models

  • Paz Ruza, Jorge
  • Alonso-Betanzos, Amparo
  • Guijarro-Berdiñas, Bertha
  • Cancela, Brais
  • Eiras-Franco, Carlos
[Abstract]: Dyadic regression models, which output real-valued predictions for pairs of entities, are fundamental in many domains [e.g., obtaining user-product ratings in recommender systems (RSs)] and promising and under exploration in others (e.g., tuning patient–drug dosages in precision pharmacology). In this work, we prove that nonuniform observed value distributions of individual entities lead to severe biases in state-of-the-art models, skewing predictions toward the average of observed past values for the entity and providing worse-than-random predictive power in eccentric yet crucial cases; we name this phenomenon eccentricity bias. We show that global error metrics like root-mean-squared error (RMSE) are insufficient to capture this bias, and we introduce eccentricity area under the curve (EAUC) as a novel metric that can quantify it in all studied domains and models. We prove the intuitive interpretation of EAUC by experimenting with naive post-training bias corrections and theorize other options to use EAUC to guide the construction of fair models. This work contributes a bias-aware evaluation of dyadic regression to prevent unfairness in critical real-world applications of such systems., This work was supported in part by MICIU/AEI/10.13039/501100011033 and ESF+ under Grant FPU21/05783; in part by MICIU/AEI/10.13039/501100011033 under Grant PID2019-109238GB-C22; in part by MICIU/AEI/10.13039/501100011033 and ERDF, EU under Grant PID2023-147404OB-I00 and Grant PID2021-128045OA-I00; in part by the Ministry for Digital Transformation and Civil Service and Next-Generation EU/PRTR under Grant TSI-100925-2023-1; in part by the Xunta de Galicia under Grant ED431C 2022/44; and in part by Consellería de Cultura, Educación e Universidade (ERDF Operational Programme Galicia 2021–2027) and Secretaría Xeral de Universidades under Grant ED431G 2023/01., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

A review of green artificial intelligence: Towards a more sustainable future

  • Bolón-Canedo, Verónica
  • Morán-Fernández, Laura
  • Cancela, Brais
  • Alonso-Betanzos, Amparo
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Green artificial intelligence (AI) is more environmentally friendly and inclusive than conventional AI, as it not only produces accurate results without increasing the computational cost but also ensures that any researcher with a laptop can perform high-quality research without the need for costly cloud servers. This paper discusses green AI as a pivotal approach to enhancing the environmental sustainability of AI systems. Described are AI solutions for eco-friendly practices in other fields (green-by AI), strategies for designing energy-efficient machine learning (ML) algorithms and models (green-in AI), and tools for accurately measuring and optimizing energy consumption. Also examined are the role of regulations in promoting green AI and future directions for sustainable ML. Underscored is the importance of aligning AI practices with environmental considerations, fostering a more eco-conscious and energy-efficient future for AI systems., This work was supported by CITIC, a Research Center accredited by Galician University System, which is funded by "Consellería de Cultura, Educación e Universidade from Xunta de Galicia", supported in an 80% through ERDF Funds, ERDF Operational Programme Galicia 2014-2020, and the remaining 20% by "Secretaría Xeral de Universidades" (Grant ED431G 2019/01). It was also partially funded by Xunta de Galicia/FEDER-UE under Grant ED431C 2022/44; Ministerio de Ciencia e Innovación MCIN/AEI/10.13039/501100011033 and "NextGenerationEU"/PRTR under Grants [PID2019-109238GB-C22; PID2021-128045OA-I00; ED2021-130599A-I00] and Ministry for Digital Transformation and Civil Service under grant TSI-100925-2023-1. Funding for open access charge: Universidade da Coruña/CISUG, Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431C 2022/44
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Performance and sustainability of BERT derivatives in dyadic data

  • Escarda Fernández, Miguel
  • Eiras-Franco, Carlos
  • Cancela, Brais
  • Guijarro-Berdiñas, Bertha
  • Alonso-Betanzos, Amparo
[Abstract]: In recent years, the Natural Language Processing (NLP) field has experienced a revolution, where numerous models – based on the Transformer architecture – have emerged to process the ever-growing volume of online text-generated data. This architecture has been the basis for the rise of Large Language Models (LLMs). Enabling their application to many diverse tasks in which they excel with just a fine-tuning process that comes right after a vast pre-training phase. However, their sustainability can often be overlooked, especially regarding computational and environmental costs. Our research aims to compare various BERT derivatives in the context of a dyadic data task while also drawing attention to the growing need for sustainable AI solutions. To this end, we utilize a selection of transformer models in an explainable recommendation setting, modeled as a multi-label classification task originating from a social network context, where users, restaurants, and reviews interact., Research funded by the Spain Ministry of Science, Innovation and Universities (MCIN/AEI/10.13039/501100011033) and ERDF “A way of making Europe” (PID2019-109238GB-C22, PID2021-128045OA-I00, PID2023-147404OB-I00), by the “Xunta de Galicia” (ED431C 2022/44) with the European Union ERDF funds, and by the Ministry for Digital Transformation and Civil Service and “Next-GenerationEU”/PRTR (Grant TSI-100925-2023-1). CITIC, as Research Center accredited by Galician University System, is funded by “Consellería de Cultura, Educación e Universidade from Xunta de Galicia ”, supported in an 80% through ERDF Operational Programme Galicia 2014-2020, and the remaining 20% by “Secretaría Xeral de Universidades” (Grant ED431G 2023/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Sustainable transparency on recommender systems: Bayesian ranking of images for explainability

  • Paz Ruza, Jorge
  • Alonso-Betanzos, Amparo
  • Guijarro-Berdiñas, Bertha
  • Cancela, Brais
  • Eiras-Franco, Carlos
[Abstract]: Recommender Systems have become crucial in the modern world, commonly guiding users towards relevant content or products, and having a large influence over the decisions of users and citizens. However, ensuring transparency and user trust in these systems remains a challenge; personalized explanations have emerged as a solution, offering justifications for recommendations. Among the existing approaches for generating personalized explanations, using existing visual content created by users is a promising option to maximize transparency and user trust. State-of-the-art models that follow this approach, despite leveraging highly optimized architectures, employ surrogate learning tasks that do not efficiently model the objective of ranking images as explanations for a given recommendation; this leads to a suboptimal training process with high computational costs that may not be reduced without affecting model performance. This work presents BRIE, a novel model where we leverage Bayesian Pairwise Ranking to enhance the training process, allowing us to consistently outperform state-of-the-art models in six real-world datasets while reducing its model size by up to 64 times and its CO2 emissions by up to 75% in training and inference., This research work has been funded by MICIU/AEI /10.13039/501100011033 and ESF+ (grant FPU21/05783), ERDF A way of making Europe (PID2019-109238GB-C22) and ERDF/EU (PID2021-128045OA-I00), and by the Xunta de Galicia, Spain (Grant ED431C 2022/44) with the European Union ERDF funds. CITIC, as Research Center accredited by Galician University System, is funded by “Consellería de Cultura, Educación e Universidade from Xunta de Galicia ”, supported in an 80% through ERDF Operational Programme Galicia 2014–2020, and the remaining 20% by “Secretaría Xeral de Universidades” (Grant ED431G 2019/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Contribución de congreso (ConferenceOutput)

Explicabilidad Sostenible para Sistemas de Recomendación mediante Ranking Bayesiano de Imágenes

  • Paz Ruza, Jorge
  • Alonso-Betanzos, Amparo
  • Guijarro-Berdiñas, Bertha
  • Eiras-Franco, Carlos
  • Cancela, Brais
Dataset depositado no repositorio: https://zenodo.org/records/14622324, Presentado na XX Conferencia de la Asociación Española para la Inteligencia Artificial (CAEPIA 2024), organizado por Asociación Española para la Inteligencia Artificial (AEPIA), A Coruña, 19 al 21 de junio de 2024, [Abstract]: Los Sistemas de Recomendacion se han vuelto cruciales por su gran influencia en la sociedad pero, siendo mayoritariamente sistemas de caja negra, fomentar su transparencia es tan primordial como complejo; utilizar contenido visual creado por los usuarios para explicar nuevas recomendaciones es una opcion prometedora para maximizar su confianza. Los algoritmos existentes presentan arquitecturas altamente optimizadas pero modelan de forma indirecta y suboptima la selección de mejores imagenes como explicaciones, provocando un entrenamiento ineficiente y un alto coste computacional que no puede ser reducido sin afectar al rendimiento del modelo. Este trabajo presenta BRIE, un nuevo modelo basado en Ranking Bayesiano por Pares que mejora el proceso de entrenamiento, supera al Estado del Arte en conjuntos de datos reales, y reduce en un 98 % el tamano de los modelos y en un 75 % las emisiones de CO2., Este trabajo esta financiado por MICIU/AEI/10.13039/501100011033/ y FEDER Una manera de hacer Europa (PID2019-109238GB-C22), MICIU/AEI/10.13039/501100011033/ y el FSE+ (FPU21/05783), MICIU/AEI /10.13039/501100011033 y FEDER, UE (PID2021-128045OA-I00), y la Xunta de Galicia (ED431C 2022/44) mediante fondos ERDF de la Union Europea. CITIC, como Centro de Investigacion acreditado por el Sistema Universitario Galego, esta financiado por la Consellería de Cultura, Educación e Universidades de la Xunta de Galicia, apoyado un 80 % por el Programa Operacional ERDF Galicia 2014-2020, y un 20 % por la Secretaría Xeral de Universidades de la Xunta de Galicia (ED431G 2019/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2019/01