Multi-Attribute, Multimodal Bias Mitigation in AI Systems

Projektinformationen

MAMMOth

ID Finanzhilfevereinbarung: 101070285

DOI

10.3030/101070285

Projekt abgeschlossen

EK-Unterschriftsdatum 20 Juni 2022

Startdatum 1 November 2022

Enddatum 31 Oktober 2025

Finanziert unter

• Digital, Industry and Space

Gesamtkosten

€ 3 304 975,00

EU-Beitrag

€ 3 304 975,00

Koordiniert durch

ETHNIKO KENTRO EREVNAS KAI TECHNOLOGIKIS ANAPTYXIS
Greece

CORDIS bietet Links zu öffentlichen Ergebnissen und Veröffentlichungen von HORIZONT-Projekten.

Links zu Ergebnissen und Veröffentlichungen von RP7-Projekten sowie Links zu einigen Typen spezifischer Ergebnisse wie Datensätzen und Software werden dynamisch von OpenAIRE abgerufen.

Leistungen

Documents, reports (11)

Explainable Methods for Discovering Bias in Multimodal Data

Report on outcomes of activities T2.3 and T2.4, focusing on the interaction between multimodal data and multi-attribute network analysis streams and the development of explainable bias analysis methods.

Methods and Algorithms for Multidimensional Fairness in Multi-attribute Networks

Report on research for mitigating multi-dimensional discrimination in multi-attribute networks.

Methods and Algorithms for Multidimensional Fairness-aware Classification

Report on methods for mitigating bias in multi-dimensional classification problems.

Multi-dimensional Discrimination Definitions and Operational Measures

Report on operational definitions and measures for multi-dimensional fairness.

Stakeholder Evaluation of System, Processes and Results

This summarizes and prioritizes the results of the three pilots, along with the assessment of the reliability of their methodological aspects. The report will further suggest measures that could form the basis for changes in formal legislation.

MAMMOth's Handbook: Best practices

Consolidated training and awareness raising material on preventing gender and intersectional bias for AI researchers, students and practitioners.

Final DCE and Policy Report

Report containing updates on DCE activities (CSI), standardization (CSI) and policy advice (TRI).

Methods and Algorithms for Bias-aware Multimodal attribute Extraction

Report on methods for assessing the bias of AI multimodal attribute extraction models and on improved models that do not discriminate against protected or sensitive groups.

Methods and Algorithms for Bias Analysis in Multi-attribute Networks

Report on methods for bias analysis and modeling multi-attribute networks.

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.

Evaluation and Mitigation of Bias in the use cases

This summarizes the findings of applying the MAMMOth toolkit and methods on the three pilots.

Other (1)

MAMMOth Bias Toolkit

Software toolkit for bias exploration, evaluation and mitigation. A first and second version of the toolkit will be released on M18 (MS4) and M26 (MS5) respectively.

Data Management Plan (1)

Data Management Plan

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

Veröffentlichungen

Conference proceedings (19)

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

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

FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data

Autoren: 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
Veröffentlicht in: FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data
Herausgeber: Elsevier BV
DOI: 10.1109/WACVW60836.2024.00100

MMM-fair: An Interactive Toolkit for Exploring and Operationalizing Multi-Fairness Trade-offs

Autoren: Swati Swati, Arjun Roy, Emmanouil Panagiotou, Eirini Ntoutsi
Veröffentlicht in: Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025
Herausgeber: ACM
DOI: 10.1145/3746252.3761476

Badd: Bias mitigation through bias addition

Autoren: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Veröffentlicht in: 2025
Herausgeber: IEEE/CVF

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

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

FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning

Autoren: Arjun Roy, Christos Koutlis, Symeon Papadopoulos, Eirini Ntoutsi
Veröffentlicht in: 2024 International Joint Conference on Neural Networks (IJCNN), 2024
Herausgeber: IEEE
DOI: 10.1109/IJCNN60899.2024.10651221

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

Autoren: Elmokhtar Mohamed Moussa, Ioannis Sarridis, Emmanouil Krasanakis, Nathan Ramoly, Symeon Papadopoulos, Ahmad Montaser Awal, Lara Younes
Veröffentlicht in: Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops, Ausgabe pp. 1421-1428, 2025
Herausgeber: CVF

A Deep Latent Factor Graph Clustering with Fairness-Utility Trade-off Perspective

Autoren: Siamak Ghodsi, Amjad Seyedi, Tai Le Quy, Fariba Karimi, and Eirini Ntoutsi
Herausgeber: IEEE

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

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

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

Autoren: """Swati, Swati, Arjun Roy, Eirini Ntoutsi """
Veröffentlicht in: 2024
Herausgeber: EWAF 2024
DOI: 10.48550/ARXIV.2407.16892

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

Autoren: Arjun Roy, Jan Horstmann, Eirini Ntoutsi
Veröffentlicht in: 2023 ACM Conference on Fairness, Accountability, and Transparency, 2025
Herausgeber: ACM
DOI: 10.1145/3593013.3593979

Adversarial Robustness of VAEs across Intersectional Subgroups

Autoren: Ramanaik, Chethan Krishnamurthy and Roy, Arjun and Ntoutsi, Eirini
Veröffentlicht in: 2024
Herausgeber: 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

Autoren: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Veröffentlicht in: Proceedings of the 2024 International Conference on Multimedia Retrieval, 2025
Herausgeber: ACM
DOI: 10.1145/3652583.3658007

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

Autoren: Panagiotou, Emmanouil and Roy, Arjun and Ntoutsi, Eirini
Veröffentlicht in: 2024
Herausgeber: 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

Autoren: Arjun Roy, Stavroula Rizou, Symeon Papadopoulos, Eirini Ntoutsi
Veröffentlicht in: Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, 2025, ISBN 9798400714825
Herausgeber: ACM
DOI: 10.1145/3715275.3732125

Learning impartial policies for sequential counterfactual explanations using Deep Reinforcement Learning

Autoren: Emmanouil Panagiotou, Eirini Ntoutsi
Veröffentlicht in: 2025
Herausgeber: Springer, Cham
DOI: 10.1007/978-3-031-74630-7_24

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

Autoren: Georgia Baltsou, Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos
Veröffentlicht in: 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), 2024
Herausgeber: IEEE
DOI: 10.1109/FG59268.2024.10581864

Towards Standardizing AI Bias Exploration

Autoren: Emmanouil Krasanakis, Symeon Papadopoulos
Veröffentlicht in: Workshop on AI bias: Measurements, Mitigation, Explanation Strategies (AIMMES 2024), 2024, ISSN 2331-8422
Herausgeber: 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

Autoren: Emmanouil Panagiotou, Manuel Heurich, Tim Landgraf, Eirini Ntoutsi
Veröffentlicht in: Proceedings of the 5th ACM International Conference on AI in Finance, 2024
Herausgeber: ACM
DOI: 10.1145/3677052.3698673

Peer reviewed articles (12)

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

Autoren: Ian Slesinger, Evren Yalaz, Stavroula Rizou, Marta Gibin, Emmanouil Krasanakis, Symeon Papadopoulos
Veröffentlicht in: Societies, Ausgabe 14, 2024, ISSN 2075-4698
Herausgeber: MDPI AG
DOI: 10.3390/SOC14120259

Universal Local Attractors on Graphs

Autoren: Emmanouil Krasanakis, Symeon Papadopoulos, Ioannis Kompatsiaris
Veröffentlicht in: Applied Sciences, Ausgabe 14, 2024, ISSN 2076-3417
Herausgeber: MDPI AG
DOI: 10.3390/APP14114533

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

Autoren: 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
Veröffentlicht in: FRCSyn-onGoing: Benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems, 2024, ISSN 1566-2535
Herausgeber: Elsevier
DOI: 10.1016/j.inffus.2024.102322

Negotiating AI fairness: a call for rebalancing power relations

Autoren: Marta Gibin, Emmanouil Krasanakis, Kęstutis Grumodas
Veröffentlicht in: AI & SOCIETY, 2025, ISSN 0951-5666
Herausgeber: Springer Science and Business Media LLC
DOI: 10.1007/S00146-025-02653-8

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

Autoren: Ioannis Sarridis; Christos Koutlis; Symeon Papadopoulos; Christos Diou
Veröffentlicht in: Proceedings of BIAS 2023 Workshop, ECML/PKDD, 2023, ISSN 2331-8422
Herausgeber: Proceedings of BIAS 2023 Workshop, ECML/PKDD
DOI: 10.48550/arxiv.2307.10011

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

Autoren: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Veröffentlicht in: IEEE Transactions on Pattern Analysis and Machine Intelligence, Ausgabe 47, 2024, ISSN 0162-8828
Herausgeber: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TPAMI.2024.3487254

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

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

Assortative and preferential attachment lead to core-periphery networks

Autoren: Javier Ureña-Carrión, Fariba Karimi, Gerardo Íñiguez, Mikko Kivelä
Veröffentlicht in: Physical Review Research, Ausgabe 5, 2023, ISSN 2643-1564
Herausgeber: American Physical Society (APS)
DOI: 10.1103/PHYSREVRESEARCH.5.043287

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

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

On the inadequacy of nominal assortativity for assessing homophily in networks

Autoren: Fariba Karimi, Marcos Oliveira
Veröffentlicht in: Scientific Reports, Ausgabe 13, 2024, ISSN 2045-2322
Herausgeber: Springer Science and Business Media LLC
DOI: 10.1038/S41598-023-48113-5

Young children’s understanding of AI

Autoren: Dagmar Mercedes Heeg, Lucy Avraamidou
Veröffentlicht in: Education and Information Technologies, 2024, ISSN 1573-7608
Herausgeber: Springer Nature
DOI: 10.1007/S10639-024-13169-X

Improving the visibility of minorities through network growth interventions

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

Book chapters (1)

Sampling Strategies for Mitigating Bias in Face Synthesis Methods

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