Bayesian Models and Algorithms for Fairness and Transparency

Informazioni relative al progetto

BayesianGDPR

ID dell’accordo di sovvenzione: 851538

DOI

10.3030/851538

Progetto chiuso

Data della firma CE 28 Gennaio 2020

Data di avvio 1 Aprile 2020

Data di completamento 30 Settembre 2025

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 443 697,00

Contributo UE

€ 1 443 697,00

Coordinato da

THE UNIVERSITY OF SUSSEX
United Kingdom

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Peer reviewed articles (5)

Preserving the Fairness Guarantees of Classifiers in Changing Environments: a Survey

Autori: Ainhize Barrainkua, Paula Gordaliza, Jose A. Lozano, Novi Quadrianto
Pubblicato in: ACM Computing Surveys, 2023, ISSN 0360-0300
Editore: Association for Computing Machinary, Inc.
DOI: 10.1145/3637438

Addressing Attribute Bias with Adversarial Support-Matching

Autori: Thomas Kehrenberg, Myles Bartlett, Viktoriia Sharmanska, Novi Quadrianto
Pubblicato in: Transactions on Machine Learning Research, 2024, ISSN 2835-8856
Editore: OpenReview
DOI: 10.48550/arxiv.2203.13154

Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning

Autori: Gergely D. Németh, Miguel Ángel Lozano, Novi Quadrianto, Nuria Oliver
Pubblicato in: IEEE Access, Numero 13, 2025, Pagina/e 40258-40274, ISSN 2169-3536
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2025.3546478

A Snapshot of the Frontiers of Client Selection in Federated Learning

Autori: Gergely Dániel Németh, Miguel Ángel Lozano, Novi Quadrianto, Nuria Oliver
Pubblicato in: Transactions on Machine Learning Research, 2022, ISSN 2835-8856
Editore: OpenReview
DOI: 10.48550/arxiv.2210.04607

Causal Datasheet for Datasets: An Evaluation Guide for Real-World Data Analysis and Data Collection Design Using Bayesian Networks

Autori: Bradley Butcher, Vincent S. Huang, Christopher Robinson, Jeremy Reffin, Sema K. Sgaier, Grace Charles, Novi Quadrianto
Pubblicato in: Frontiers in Artificial Intelligence, Numero 4, 2021, ISSN 2624-8212
Editore: [Lausanne]: Frontiers Media S.A., [2018]-
DOI: 10.3389/frai.2021.612551

Other (3)

Addressing Membership Inference Attack in Federated Learning with Model Compression

Autori: Gergely Dániel Németh, Miguel Ángel Lozan, Novi Quadrianto, Nuria Oliver
Pubblicato in: 2023
Editore: arXiv

The Decoupled Risk Landscape in Performative Prediction

Autori: Javier Sanguino, Thomas Kehrenberg, José Antonio Lozano, Novi Quadrianto
Pubblicato in: 2025
Editore: arXiv
DOI: 10.48550/arxiv.2506.09044

Contrastive Examples for Addressing the Tyranny of the Majority

Autori: Sharmanska, Viktoriia; Hendricks, Lisa Anne; Darrell, Trevor; Quadrianto, Novi
Pubblicato in: Numero 1, 2020
Editore: N/A

Conference proceedings (9)

Are Compressed Language Models Less Subgroup Robust?

Autori: Leonidas Gee, Andrea Zugarini, Novi Quadrianto
Pubblicato in: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023, Pagina/e 15859-15868
Editore: Association for Computational Linguistics
DOI: 10.18653/v1/2023.emnlp-main.983

Racial Disparities in the Enforcement of Marijuana Violations in the US

Autori: Butcher, Bradley; Robinson, Chris; Zilka, Miri; Fogliato, Riccardo; Ashurst, Carolyn; Weller, Adrian
Pubblicato in: AIES '22: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 2022, ISBN 9781450392471
Editore: Association for Computing Machinery
DOI: 10.1145/3514094.3534184

RealPatch: A Statistical Matching Framework for Model Patching with Real Samples

Autori: Sara Romiti, Christopher Inskip, Viktoriia Sharmanska, Novi Quadrianto
Pubblicato in: Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXV, 2022, Pagina/e 146–162, ISBN 978-3-031-19805-2
Editore: Springer-Verlag
DOI: 10.1007/978-3-031-19806-9_9

FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selection

Autori: Gergely D. Németh, Eros Fanì, Yeat Jeng Ng, Barbara Caputo, Miguel Ángel Lozano, Nuria Oliver, Novi Quadrianto
Pubblicato in: The 3rd International Conference on Federated Learning Technologies and Applications, 2025
Editore: IEEE

Null-Sampling for Interpretable and Fair Representations

Autori: Thomas Kehrenberg, Myles Bartlett, Oliver Thomas, Novi Quadrianto
Pubblicato in: Computer Vision – ECCV 2020 - 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXVI, 2020, Pagina/e 565-580, ISBN 978-3-030-58573-0
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-58574-7_34

Okapi: Generalising Better by Making Statistical Matches Match

Autori: Myles Bartlett, Sara Romiti, Viktoriia Sharmanska, Novi Quadrianto
Pubblicato in: Advances in Neural Information Processing Systems 35 (NeurIPS 2022), 2022
Editore: Curran Associates, Inc.

An Algorithmic Framework for Positive Action

Autori: Oliver Thomas, Miri Zilka, Adrian Weller, Novi Quadrianto
Pubblicato in: Equity and Access in Algorithms, Mechanisms, and Optimization, 2021, Pagina/e 1-13, ISBN 9781450385534
Editore: ACM
DOI: 10.1145/3465416.3483303

Disagreement-based Active Learning for Robustness Against Subpopulation Shifts

Autori: Yeat Jeng Ng, Viktoriia Sharmanska, Thomas Kehrenberg, Anastasia Pentina, Novi Quadrianto
Pubblicato in: Communications in Computer and Information Science, 2024
Editore: Springer Nature

Uncertainty Matters: Stable Conclusions under Unstable Assessment of Fairness Results

Autori: Ainhize Barrainkua, Paula Gordaliza, Jose A. Lozano, Novi Quadrianto
Pubblicato in: International Conference on Artificial Intelligence and Statistics, 2024
Editore: Proceedings of Machine Learning Research
DOI: 10.48550/arxiv.2302.01079

Thesis and dissertations (5)

Semi-supervised methods for distributionally-robust learning

Autori: Myles Bartlett
Pubblicato in: 2023
Editore: N/A

Fair Representations in the Data Domain

Autori: Oliver Thomas
Pubblicato in: 2022
Editore: N/A

Towards generalisation in machine learning under subpopulation shifts: active, passive, and spectral bias perspectives

Autori: Yeat Jeng Ng
Pubblicato in: 2025
Editore: University of Sussex

Statistical Matching for Vision Tasks: Mitigating Spurious Correlations and Out-Of-Distribution Generalization

Autori: Sara Romiti
Pubblicato in: 2023
Editore: N/A

Relaxing Core Assumptions: the Impact of Data, Model and Participation Heterogeneity on Performance, Privacy and Fairness in Federated Learning

Autori: Gergely Dániel Németh
Pubblicato in: 2025
Editore: University of Alicante