Multi-Attribute, Multimodal Bias Mitigation in AI Systems

Informacje na temat projektu

MAMMOth

Identyfikator umowy o grant: 101070285

DOI

10.3030/101070285

Data podpisania przez KE 20 Czerwca 2022

Data rozpoczęcia 1 Listopada 2022

Data zakończenia 31 Października 2025

Finansowanie w ramach

• Digital, Industry and Space

Koszt całkowity

€ 3 304 975,00

Wkład UE

€ 3 304 975,00

Koordynowany przez

ETHNIKO KENTRO EREVNAS KAI TECHNOLOGIKIS ANAPTYXIS
Greece

CORDIS oferuje możliwość skorzystania z odnośników do publicznie dostępnych publikacji i rezultatów projektów realizowanych w ramach programów ramowych HORYZONT.

Odnośniki do rezultatów i publikacji związanych z poszczególnymi projektami 7PR, a także odnośniki do niektórych konkretnych kategorii wyników, takich jak zbiory danych i oprogramowanie, są dynamicznie pobierane z systemu OpenAIRE .

Rezultaty

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.

Publikacje

Conference proceedings (17)

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

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

Badd: Bias mitigation through bias addition

Autorzy: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Opublikowane w: 2025
Wydawca: IEEE/CVF

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

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

FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning

Autorzy: Arjun Roy, Christos Koutlis, Symeon Papadopoulos, Eirini Ntoutsi
Opublikowane w: 2024 International Joint Conference on Neural Networks (IJCNN), 2024
Wydawca: IEEE
DOI: 10.1109/IJCNN60899.2024.10651221

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

Autorzy: Elmokhtar Mohamed Moussa, Ioannis Sarridis, Emmanouil Krasanakis, Nathan Ramoly, Symeon Papadopoulos, Ahmad Montaser Awal, Lara Younes
Opublikowane w: Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops, Numer pp. 1421-1428, 2025
Wydawca: CVF

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

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

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

Autorzy: Arjun Roy, Jan Horstmann, Eirini Ntoutsi
Opublikowane w: """Multi-dimensional discrimination in Law and Machine Learning - A comparative overview""", 2023, ISBN 9798400701924
Wydawca: ACM FAccT
DOI: 10.1145/3593013.3593979

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

Autorzy: """Swati, Swati, Arjun Roy, Eirini Ntoutsi """
Opublikowane w: 2024
Wydawca: EWAF 2024
DOI: 10.48550/ARXIV.2407.16892

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

Autorzy: Arjun Roy, Jan Horstmann, Eirini Ntoutsi
Opublikowane w: 2023 ACM Conference on Fairness, Accountability, and Transparency, 2025
Wydawca: ACM
DOI: 10.1145/3593013.3593979

Adversarial Robustness of VAEs across Intersectional Subgroups

Autorzy: Ramanaik, Chethan Krishnamurthy and Roy, Arjun and Ntoutsi, Eirini
Opublikowane w: 2024
Wydawca: 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

Autorzy: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Opublikowane w: Proceedings of the 2024 International Conference on Multimedia Retrieval, 2025
Wydawca: ACM
DOI: 10.1145/3652583.3658007

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

Autorzy: Panagiotou, Emmanouil and Roy, Arjun and Ntoutsi, Eirini
Opublikowane w: 2024
Wydawca: 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

Autorzy: Arjun Roy, Stavroula Rizou, Symeon Papadopoulos, Eirini Ntoutsi
Opublikowane w: Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, 2025, ISBN 9798400714825
Wydawca: ACM
DOI: 10.1145/3715275.3732125

Learning impartial policies for sequential counterfactual explanations using Deep Reinforcement Learning

Autorzy: Emmanouil Panagiotou, Eirini Ntoutsi
Opublikowane w: 2025
Wydawca: Springer, Cham
DOI: 10.1007/978-3-031-74630-7_24

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

Autorzy: Georgia Baltsou, Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos
Opublikowane w: 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), 2024
Wydawca: IEEE
DOI: 10.1109/FG59268.2024.10581864

Towards Standardizing AI Bias Exploration

Autorzy: Emmanouil Krasanakis, Symeon Papadopoulos
Opublikowane w: Workshop on AI bias: Measurements, Mitigation, Explanation Strategies (AIMMES 2024), 2024, ISSN 2331-8422
Wydawca: 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

Autorzy: Emmanouil Panagiotou, Manuel Heurich, Tim Landgraf, Eirini Ntoutsi
Opublikowane w: Proceedings of the 5th ACM International Conference on AI in Finance, 2024
Wydawca: ACM
DOI: 10.1145/3677052.3698673

Peer reviewed articles (13)

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

Autorzy: Ian Slesinger, Evren Yalaz, Stavroula Rizou, Marta Gibin, Emmanouil Krasanakis, Symeon Papadopoulos
Opublikowane w: Societies, Numer 14, 2024, ISSN 2075-4698
Wydawca: MDPI AG
DOI: 10.3390/SOC14120259

Universal Local Attractors on Graphs

Autorzy: Emmanouil Krasanakis, Symeon Papadopoulos, Ioannis Kompatsiaris
Opublikowane w: Applied Sciences, Numer 14, 2024, ISSN 2076-3417
Wydawca: MDPI AG
DOI: 10.3390/APP14114533

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

Autorzy: 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
Opublikowane w: FRCSyn-onGoing: Benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems, 2024, ISSN 1566-2535
Wydawca: Elsevier
DOI: 10.1016/j.inffus.2024.102322

Assortative and preferential attachment lead to core-periphery networks

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

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

Autorzy: Ioannis Sarridis; Christos Koutlis; Symeon Papadopoulos; Christos Diou
Opublikowane w: Proceedings of BIAS 2023 Workshop, ECML/PKDD, 2023, ISSN 2331-8422
Wydawca: Proceedings of BIAS 2023 Workshop, ECML/PKDD
DOI: 10.48550/arxiv.2307.10011

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

Autorzy: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Opublikowane w: IEEE Transactions on Pattern Analysis and Machine Intelligence, Numer 47, 2024, ISSN 0162-8828
Wydawca: Institute of Electrical and Electronics Engineers (IEEE)
DOI: 10.1109/TPAMI.2024.3487254

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

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

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

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

Assortative and preferential attachment lead to core-periphery networks

Autorzy: Javier Ureña-Carrión, Fariba Karimi, Gerardo Íñiguez, Mikko Kivelä
Opublikowane w: Physical Review Research, Numer 5, 2023, ISSN 2643-1564
Wydawca: American Physical Society (APS)
DOI: 10.1103/PHYSREVRESEARCH.5.043287

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

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

On the inadequacy of nominal assortativity for assessing homophily in networks

Autorzy: Fariba Karimi, Marcos Oliveira
Opublikowane w: Scientific Reports, Numer 13, 2024, ISSN 2045-2322
Wydawca: Springer Science and Business Media LLC
DOI: 10.1038/S41598-023-48113-5

Young children’s understanding of AI

Autorzy: Dagmar Mercedes Heeg, Lucy Avraamidou
Opublikowane w: Education and Information Technologies, 2024, ISSN 1573-7608
Wydawca: Springer Nature
DOI: 10.1007/S10639-024-13169-X

Improving the visibility of minorities through network growth interventions

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

Book chapters (1)

Sampling Strategies for Mitigating Bias in Face Synthesis Methods

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