Multi-Attribute, Multimodal Bias Mitigation in AI Systems

Informations projet

MAMMOth

N° de convention de subvention: 101070285

DOI

10.3030/101070285

Date de signature de la CE 20 Juin 2022

Date de début 1 Novembre 2022

Date de fin 31 Octobre 2025

Financé au titre de

• Digital, Industry and Space

Coût total

€ 3 304 975,00

Contribution de l’UE

€ 3 304 975,00

Coordonné par

ETHNIKO KENTRO EREVNAS KAI TECHNOLOGIKIS ANAPTYXIS
Greece

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Data Management Plan (1)

Data Management Plan

First version of the Data Management Plan. It will be maintained and updated internally throughout the project.

Documents, reports (1)

User Requirements and Architecture

This report will document the activities, methodology and outcomes of the co-creation and analysis of system/user requirements and will outline the overall architecture of the MAMMoth bias toolkit. UNIBO will be in charge of the user requirements analysis, EXUS will lead the toolkit architecture design, and CERTH will coordinate the overall process and writing of the deliverable.

Publications

Conference proceedings (17)

hyperFA*IR: A hypergeometric approach to fair rankings with finite candidate pool

Auteurs: Mauritz N. Cartier van Dissel, Samuel Martin-Gutierrez, Lisette Espín-Noboa, Ana María Jaramillo, Fariba Karimi
Publié dans: Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, 2025
Éditeur: ACM
DOI: 10.1145/3715275.3732143

Badd: Bias mitigation through bias addition

Auteurs: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Publié dans: 2025
Éditeur: IEEE/CVF

Studying bias in visual features through the lens of optimal transport.

Auteurs: Simone Fabbrizzi, Xuan Zhao, Emmanouil Krasanakis, Symeon Papadopoulos, and Eirini Ntoutsi
Publié dans: Studying bias in visual features through the lens of optimal transport., 2023
Éditeur: Data Mining and Knowledge Discovery
DOI: 10.1007/s10618-023-00972-2

FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning

Auteurs: Arjun Roy, Christos Koutlis, Symeon Papadopoulos, Eirini Ntoutsi
Publié dans: 2024 International Joint Conference on Neural Networks (IJCNN), 2024
Éditeur: IEEE
DOI: 10.1109/IJCNN60899.2024.10651221

Face-swapping based Data Augmentation for ID Document and Selfie Face Verification

Auteurs: Elmokhtar Mohamed Moussa, Ioannis Sarridis, Emmanouil Krasanakis, Nathan Ramoly, Symeon Papadopoulos, Ahmad Montaser Awal, Lara Younes
Publié dans: Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops, Numéro pp. 1421-1428, 2025
Éditeur: CVF

Towards Cohesion-Fairness Harmony: Contrastive Regularization in Individual Fair Graph Clustering

Auteurs: Ghodsi, S., Amjad Seyedi, S., and Ntoutsi, E
Publié dans: Towards Cohesion-Fairness Harmony: Contrastive Regularization in Individual Fair Graph Clustering, 2024, ISBN 978-981-97-2242-6
Éditeur: Springer, Singapore
DOI: 10.1007/978-981-97-2242-6_23

"""Multi-dimensional discrimination in Law and Machine Learning - A comparative overview"""

Auteurs: Arjun Roy, Jan Horstmann, Eirini Ntoutsi
Publié dans: """Multi-dimensional discrimination in Law and Machine Learning - A comparative overview""", 2023, ISBN 9798400701924
Éditeur: ACM FAccT
DOI: 10.1145/3593013.3593979

Exploring Fusion Techniques in Multimodal AI-Based Recruitment: Insights from FairCVdb

Auteurs: """Swati, Swati, Arjun Roy, Eirini Ntoutsi """
Publié dans: 2024
Éditeur: EWAF 2024
DOI: 10.48550/ARXIV.2407.16892

Multi-dimensional Discrimination in Law and Machine Learning - A Comparative Overview

Auteurs: Arjun Roy, Jan Horstmann, Eirini Ntoutsi
Publié dans: 2023 ACM Conference on Fairness, Accountability, and Transparency, 2025
Éditeur: ACM
DOI: 10.1145/3593013.3593979

Adversarial Robustness of VAEs across Intersectional Subgroups

Auteurs: Ramanaik, Chethan Krishnamurthy and Roy, Arjun and Ntoutsi, Eirini
Publié dans: 2024
Éditeur: Accepted in the BIAS workshop, co-located with ECML PKDD 2024
DOI: 10.48550/ARXIV.2407.03864

FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations

Auteurs: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Publié dans: Proceedings of the 2024 International Conference on Multimedia Retrieval, 2025
Éditeur: ACM
DOI: 10.1145/3652583.3658007

Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study

Auteurs: Panagiotou, Emmanouil and Roy, Arjun and Ntoutsi, Eirini
Publié dans: 2024
Éditeur: Accepted in the BIAS workshop, co-located with ECML PKDD 2024
DOI: 10.48550/ARXIV.2409.05215

Achieving Socio-Economic Parity through the Lens of EU AI Act

Auteurs: Arjun Roy, Stavroula Rizou, Symeon Papadopoulos, Eirini Ntoutsi
Publié dans: Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, 2025, ISBN 9798400714825
Éditeur: ACM
DOI: 10.1145/3715275.3732125

Learning impartial policies for sequential counterfactual explanations using Deep Reinforcement Learning

Auteurs: Emmanouil Panagiotou, Eirini Ntoutsi
Publié dans: 2025
Éditeur: Springer, Cham
DOI: 10.1007/978-3-031-74630-7_24

SDFD: Building a Versatile Synthetic Face Image Dataset with Diverse Attributes

Auteurs: Georgia Baltsou, Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos
Publié dans: 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), 2024
Éditeur: IEEE
DOI: 10.1109/FG59268.2024.10581864

Towards Standardizing AI Bias Exploration

Auteurs: Emmanouil Krasanakis, Symeon Papadopoulos
Publié dans: Workshop on AI bias: Measurements, Mitigation, Explanation Strategies (AIMMES 2024), 2024, ISSN 2331-8422
Éditeur: Workshop on AI bias: Measurements, Mitigation, Explanation Strategies (AIMMES 2024)
DOI: 10.48550/arXiv.2405.19022

TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAE

Auteurs: Emmanouil Panagiotou, Manuel Heurich, Tim Landgraf, Eirini Ntoutsi
Publié dans: Proceedings of the 5th ACM International Conference on AI in Finance, 2024
Éditeur: ACM
DOI: 10.1145/3677052.3698673

Peer reviewed articles (13)

Training in Co-Creation as a Methodological Approach to Improve AI Fairness

Auteurs: Ian Slesinger, Evren Yalaz, Stavroula Rizou, Marta Gibin, Emmanouil Krasanakis, Symeon Papadopoulos
Publié dans: Societies, Numéro 14, 2024, ISSN 2075-4698
Éditeur: MDPI AG
DOI: 10.3390/SOC14120259

Universal Local Attractors on Graphs

Auteurs: Emmanouil Krasanakis, Symeon Papadopoulos, Ioannis Kompatsiaris
Publié dans: Applied Sciences, Numéro 14, 2024, ISSN 2076-3417
Éditeur: MDPI AG
DOI: 10.3390/APP14114533

FRCSyn-onGoing: Benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems

Auteurs: Pietro Melzi, Ruben Tolosana, Ruben Vera-Rodriguez, Minchul Kim, Christian Rathgeb, Xiaoming Liu, Ivan DeAndres-Tame, Aythami Morales, Julian Fierrez, Javier Ortega-Garcia, Weisong Zhao, Xiangyu Zhu, Zheyu Yan, Xiao-Yu Zhang, Jinlin Wu, Zhen Lei, Suvidha
Publié dans: FRCSyn-onGoing: Benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems, 2024, ISSN 1566-2535
Éditeur: Elsevier
DOI: 10.1016/j.inffus.2024.102322

Assortative and preferential attachment lead to core-periphery networks

Auteurs: Ureña-Carrion, J., Karimi, F., Iñiguez, G., & Kivelä, M. (2023)
Publié dans: Assortative and preferential attachment lead to core-periphery networks, 2023, ISSN 2643-1564
Éditeur: PHYSICAL REVIEW RESEARCH
DOI: 10.1103/PhysRevResearch.5.043287

Towards Fair Face Verification: An In-depth Analysis of Demographic Biases

Auteurs: Ioannis Sarridis; Christos Koutlis; Symeon Papadopoulos; Christos Diou
Publié dans: Proceedings of BIAS 2023 Workshop, ECML/PKDD, 2023, ISSN 2331-8422
Éditeur: Proceedings of BIAS 2023 Workshop, ECML/PKDD
DOI: 10.48550/arxiv.2307.10011

FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations

Auteurs: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Publié dans: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numéro 47, 2024, ISSN 0162-8828
Éditeur: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TPAMI.2024.3487254

On the inadequacy of nominal assortativity for assessing homophily in networks.

Auteurs: Karimi, F., Oliveira, M.
Publié dans: On the inadequacy of nominal assortativity for assessing homophily in networks., 2023, ISSN 2045-2322
Éditeur: Nature Publishing Group
DOI: 10.1038/s41598-023-48113-5

Can we Disrupt the Momentum of the AI Colonization of Science Education?

Auteurs: Lucy Avraamidou
Publié dans: Can we Disrupt the Momentum of the AI Colonization of Science Education?, 2024, ISSN 1098-2736
Éditeur: Journal of Research in Science Teaching
DOI: 10.1002/tea.21961

Assortative and preferential attachment lead to core-periphery networks

Auteurs: Javier Ureña-Carrión, Fariba Karimi, Gerardo Íñiguez, Mikko Kivelä
Publié dans: Physical Review Research, Numéro 5, 2023, ISSN 2643-1564
Éditeur: American Physical Society (APS)
DOI: 10.1103/PHYSREVRESEARCH.5.043287

The Use of AI in school science: a Systematic Literature Review

Auteurs: Dagmar Mercedes Heeg, Lucy Avraamidou
Publié dans: The Use of AI in school science: a Systematic Literature Review, 2023, ISSN 1469-5790
Éditeur: Taylor & Francis Group
DOI: 10.1080/09523987.2023.2264990

On the inadequacy of nominal assortativity for assessing homophily in networks

Auteurs: Fariba Karimi, Marcos Oliveira
Publié dans: Scientific Reports, Numéro 13, 2024, ISSN 2045-2322
Éditeur: Springer Science and Business Media LLC
DOI: 10.1038/S41598-023-48113-5

Young children’s understanding of AI

Auteurs: Dagmar Mercedes Heeg, Lucy Avraamidou
Publié dans: Education and Information Technologies, 2024, ISSN 1573-7608
Éditeur: Springer Nature
DOI: 10.1007/S10639-024-13169-X

Improving the visibility of minorities through network growth interventions

Auteurs: Leonie Neuhäuser, Fariba Karimi, Jan Bachmann, Markus Strohmaier, Michael T Schaub
Publié dans: Improving the visibility of minorities through network growth interventions, 2023, ISSN 2399-3650
Éditeur: Communications Physics
DOI: 10.1038/s42005-023-01218-9

Book chapters (1)

Sampling Strategies for Mitigating Bias in Face Synthesis Methods

Auteurs: Emmanouil Maragkoudakis, Symeon Papadopoulos, Iraklis Varlamis, Christos Diou
Publié dans: Communications in Computer and Information Science, Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2025
Éditeur: Springer Nature Switzerland
DOI: 10.1007/978-3-031-74630-7_16