Artificial Intelligence without Bias

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 .

Risultati finali

Research documentation on accounting for bias in results [to be updated]

Research documentation on accounting for bias in results (Leader: UNIPI, participation of SCHUFA, SOTON-LS, LUH-L3S) (M24, M42): Reports on research progress and results.

Report on WP2 Integration and application [to be updated]

Report on WP2 Integration and application (Leader: CERTH, participation of OU, GESIS-CSS, LUH-IRI) (M24, M42): Reports on integration and application activities related to bias mitigation in algorithms (in collaboration with WP4).

Research documentation on mitigating bias in algorithms [to be updated]

D2.1a/b: Research documentation on mitigating bias in algorithms (Leader: OU, participation of GESIS-CSS, CERTH, LUH-IRI) (M24, M42): Reports on research progress and results.

Training Report [to be updated]

Training Report (Leader: UNI-KLU; participation: all) (M24, M48). Reports on planning and implementation of training activities and resources.

Report on use cases and applications

Report on use cases and applications (Leader: SCHUFA, participation: all) (M42). Report on the application of the NoBIAS research in real use cases.

Report on WP3 integration and application [to be updated]

Report on WP3 integration and application (Leader: SCHUFA, participation of UNIPI, SOTON-LS, LUH-L3S) (M24, M42): Reports on integration and application activities related to accounting for bias in results (in collaboration with WP4).

Report on WP1 integration and application [to be updated]

Report on WP1 integration and application (Leader: LUH-L3S, participation of GESIS-DAS, CERTH, UNIPI, KULEUVEN) (M24, M42): Reports on integration and application activities related to understanding bias in data (in collaboration with WP4).

Research documentation on understanding bias in data [to be updated]

D1.1a/b: Research documentation on understanding bias in data (Leader: KULEUVEN, participation of GESIS-DAS, CERTH, UNIPI, LUH-L3S) (M24, M42): Reports on research progress and results.

PhD Theses

PhD theses (Leader: GESIS-CSS) (>M42; participation: all). Submission of PhD dissertations (this can be also after the end of the action).

Living Document on Bias

Living Document and Book on Bias SOTONECS There is to date no established resource that combines the interdisciplinary expertise necessary to address bias in AIdriven decision making NoBIAS will deliver this resource through the establishment of a living training document that will begin with core contributions from academic partners M6 and will be developed by the NoBIAS researchers as part of the interdisciplinary training stream and ultimately be published as a book M42 This process will develop substantive knowledge of interdisciplinary approaches and generic team working and collaborative writing skills

NoBIAS Best Practices and Policy Advice

NoBIAS Policy Advice and Best Practices (UNIPI): NoBIAS will promote the proactive participation of ESRs in initiatives for policy making and best practices with the results of their research and the use cases from their secondments. This will be facilitated by UNIPI's participation in the IEEE P7003 Working Group on Algorithmic Bias Considerations . An introduction to this will be given during Summer School 1. Training of ESRs will benefit from their involvement in such and similar standardization initiatives, e.g., by exploiting outcomes like conceptualizations, methodologies, recommendations, and use cases (such as the bias taxonomy being developed in IEEE P7003).

Book on Bias

Living Document and Book on Bias (SOTON-ECS): There is to date no established resource that combines the interdisciplinary expertise necessary to address bias in AI-driven decision making. NoBIAS will deliver this resource through the establishment of a “living training document” that will begin with core contributions from academic partners (M6) and will be developed by the NoBIAS researchers as part of the interdisciplinary training stream and ultimately be published as a book (M42). This process will develop substantive knowledge of interdisciplinary approaches and generic team working and collaborative writing skills.

NoBias Testbed

NoBIAS testbed (LUH-L3S): NoBIAS will create an integrated technology testbed as a crystallization point for the methods and algorithms developed in the project. It will support the evaluation of methods developed in the IRPs in a larger context, foster collaboration, and integrate results from all projects. The testbed will include an open source library of algorithms and methods developed during the project, fostering openness and reproducibility, and facilitating research on related problems.

Dissemination report [to be updated]

Dissemination Report Leader LUHL3S participation all M24 M48 Reports on the setup of the project website and social media accounts implementation of the dissemination strategy planning and implementation of the projectrelated events and activities

Pubblicazioni

Declarative Reasoning on Explanations Using Constraint Logic Programming

Autori: Laura State; Salvatore Ruggieri; Franco Turini
Pubblicato in: Logics in Artificial Intelligence, JELIA 2023, 2023, Pagina/e 132-141, ISBN 9783031436185
Editore: Springer Science and Business Media Deutschland GmbH
DOI: 10.1007/978-3-031-43619-2_10

Explanation Shift: Detecting distribution shifts on tabular data via the explanation space

Autori: https://arxiv.org/abs/2210.12369
Pubblicato in: 2022
Editore: Neural Information Processing Systems (NeurIPS 2022). Workshop on Distribution Shifts: Connecting Methods and Applications

Counterfactual Situation Testing: Uncovering Discrimination under Fairness given the Difference

Autori: Salvatore Ruggieri, Jose Manuel Alvarez
Pubblicato in: ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization 2023, 2023
Editore: ACM

Enhancing Fairness through Reweighting: A Path to Attain the Sufficiency Rule

Autori: Xuan Zhao, Klaus Broelemann, Salvatore Ruggieri and Gjergji Kasneci
Pubblicato in: European Conference on Artificial Intelligence, ECAI 2024, 2024
Editore: Accepted for publication
DOI: 10.48550/arxiv.2408.14126

Affinity Clustering Framework for Data Debiasing Using Pairwise Distribution Discrepancy

Autori: Ghodsi, Siamak; Ntoutsi, Eirini
Pubblicato in: Numero 1, 2023
Editore: CEUR Workshop Proceedings

Logic programming for XAI: A technical perspective

Autori: Laura State
Pubblicato in: ICLP Workshops, volume 2970 of CEUR Workshop Proceedings, Numero 1, 2021
Editore: CEUR-WS.org

Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems

Autori: Carlos Mougan; David Masip; Jordi Nin; Oriol Pujol
Pubblicato in: Modeling Decisions for Artificial Intelligence, Numero 5, 2021
Editore: Springer
DOI: 10.1007/978-3-030-85529-1_14

How to Data in Datathons

Autori: Mougan, Carlos; Plant, Richard; Teng, Clare; Bazzi, Marya; Cabrejas-Egea, Alvaro; Chan, Ryan Sze-Yin; Jasin, David Salvador; Stoffel, Martin; Whitaker, Kirstie Jane; Manser, Jules
Pubblicato in: Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks., Numero 1, 2023
Editore: Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks
DOI: 10.48550/arxiv.2309.09770

Desiderata for Explainable AI in statistical production systems of the European Central Bank

Autori: Carlos Mougan, Georgios Kanellos, Thomas Gottron
Pubblicato in: Workshop on bias and fairness in AI at ECMLPKDD, Numero 1, 2021
Editore: Springer International Publishing
DOI: 10.1007/978-3-030-93736-2_42

Can We Trust Fair-AI?

Autori: Ruggieri S.; Alvarez J. M.; Pugnana A.; State L.; Turini F.
Pubblicato in: AAAI Conference on Artificial Intelligence, AAAI 2023, 2023, Pagina/e 15421-15430, ISBN 9781577358800
Editore: AAAI Press
DOI: 10.1609/aaai.v37i13.26798

Reason to Explain: Interactive Contrastive Explanations (REASONX)

Autori: Laura State, Salvatore Ruggieri, Franco Turini
Pubblicato in: World Conference on eXplainable Artificial Intelligence 2023, 2023
Editore: Springer Nature

Algorithmic Tools in Public Employment Services: Towards a Jobseeker-Centric Perspective

Autori: Kristen M. Scott, Sonja Mei Wang, Milagros Miceli, Pieter Delobelle, Karolina Sztandar-Sztanderska, Bettina Berendt
Pubblicato in: 2022 ACM Conference on Fairness, Accountability, and Transparency, 2023
Editore: ACM
DOI: 10.1145/3531146.3534631

Careful Explanations: A Feminist Perspective on XAI

Autori: Laura State, Miriam Fahimi
Pubblicato in: European Workshop on Algorithmic Fairness, EWAF 2023, 2023, Pagina/e -
Editore: CEUR-WS.org

Introducing explainable supervised machine learning into interactive feedback loops for statistical production system

Autori: Carlos Mougan, George Kanellos, Johannes Micheler, Jose Martinez, Thomas Gottron
Pubblicato in: Irving Fisher Committee (IFC) - Bank of Italy workshop on Data science in central banking: Applications and tools, 2021
Editore: Arxiv

Fairness Implications of Encoding Protected Categorical Attributes

Autori: Carlos Mougan; Jose Manuel Alvarez; Salvatore Ruggieri; Steffen Staab
Pubblicato in: AAAI/ACM Conference on AI, Ethics, and Society, AIES 2023, 2023, Pagina/e 454-465, ISBN 9798400702310
Editore: Association for Computing Machinery, Inc
DOI: 10.1145/3600211.3604657

The Explanation Dialogues: Understanding How Legal Experts Reason About XAI Methods

Autori: Laura State, Alejandra Bringas Colmenarejo, Andrea Beretta, Salvatore Ruggieri, Franco Turini, Stephanie Law
Pubblicato in: European Workshop on Algorithmic Fairness, EWAF 2023, 2023, ISBN 161300733442
Editore: CEUR Workshop Proceedings

Sum of Group Error Differences: A Critical Examination of Bias Evaluation in Biometric Verification and a Dual-Metric Measure

Autori: Alaa Elobaid, Nathan Ramoly, Lara Younes, Symeon Papadopoulos, Eirini Ntoutsi, Ioannis Kompatsiaris
Pubblicato in: 2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG), Numero 2, 2024, Pagina/e 1-9
Editore: IEEE
DOI: 10.1109/fg59268.2024.10582012

The Role of Large Language Models in the Recognition of Territorial Sovereignty: An Analysis of the Construction of Legitimacy

Autori: Francisco Castillo-Eslava; Carlos Mougan; Alejandro Romero-Reche; Steffen Staab
Pubblicato in: Numero 1, 2023
Editore: European Workshop on Algorithmic Fairness (EWAF'23)
DOI: 10.48550/arxiv.2304.06030

Link recommendations: Their impact on network structure and minorities

Autori: Antonio Ferrara, Lisette Espin-Noboa, Fariba Karimi, Claudia Wagner
Pubblicato in: 14th ACM Web Science Conference 2022, 2023
Editore: ACM
DOI: 10.1145/3501247.3531583

Counterfactual Explanation for Regression via Disentanglement in Latent Space

Autori: Xuan Zhao, Klaus Broelemann, Gjergji Kasneci
Pubblicato in: 2023 IEEE International Conference on Data Mining Workshops (ICDMW), 2024
Editore: IEEE
DOI: 10.1109/icdmw60847.2023.00130

Time to Question if We Should: Data-Driven and Algorithmic Tools in Public Employment Services

Autori: Pieter Delobelle, Kristen M. Scott, Sonja Mei Wang, Milagros Miceli, David Hartmann, Tianling Yang, Elena Murasso, Karolina Sztandar-Sztanderska, Bettina Berendt
Pubblicato in: International workshop on Fair, Effective And Sustainable Talent management using data science, 2021
Editore: FEAST Workshop

Estimating Ground Truth in a Low-labelled Data Regime: A Study of Racism Detection in Spanish

Autori: Paula Reyero Lobo, Martino Mensio, Angel Pavon Perez, Vaclav Bayer, Joseph Kwarteng, Miriam Fernandez, Enrico Daga, Harith Alani
Pubblicato in: 2022
Editore: AAAI

Fairness in Agreement With European Values

Autori: Alejandra Bringas Colmenarejo, Luca Nannini, Alisa Rieger, Kristen M. Scott, Xuan Zhao, Gourab K Patro, Gjergji Kasneci, Katharina Kinder-Kurlanda
Pubblicato in: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 2023
Editore: ACM
DOI: 10.1145/3514094.3534158

Explainability in Practice: Estimating Electrification Rates from Mobile Phone Data in Senegal

Autori: Laura State; Hadrien Salat; Stefania Rubrichi; Zbigniew Smoreda
Pubblicato in: World Conference on eXplainable Artificial Intelligence, xAI 2023, 2023, Pagina/e 110-125, ISBN 9783031440663
Editore: Springer Science and Business Media Deutschland GmbH
DOI: 10.1007/978-3-031-44067-0_6

Bias in Hate Speech and Toxicity Detection

Autori: Paula Reyero Lobo
Pubblicato in: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 2023
Editore: ACM
DOI: 10.1145/3514094.3539519

Causal Fairness-Guided Dataset Reweighting using Neural Networks

Autori: Zhao X.; Broelemann K.; Ruggieri S.; Kasneci G.
Pubblicato in: IEEE International Conference on Big Data (BigData 2023), 2023, Pagina/e 1386-1394, ISBN 9798350324464
Editore: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/bigdata59044.2023.10386836

Constructing Meaningful Explanations: Logic-based Approaches

Autori: Laura State
Pubblicato in: AAAI/ACM Conference on AI, Ethics, and Society, AIES 2022, 2022, Pagina/e 916, ISBN 978-1-4503-9247-1
Editore: ACM
DOI: 10.1145/3514094.3539544

Domain Adaptive Decision Trees: Implications for Accuracy and Fairness

Autori: Jose M. Alvarez, Kristen M. Scott, Salvatore Ruggieri, Bettina Berendt
Pubblicato in: ACM Conference on Fairness, Accountability, and Transparency 2023, 2023
Editore: ACM

A survey on bias in visual datasets

Autori: Simone Fabbrizzi, Symeon Papadopoulos, Eirini Ntoutsi, Ioannis Kompatsiaris
Pubblicato in: Computer Vision and Image Understanding, Numero 223, 2024, Pagina/e 103552, ISSN 1077-3142
Editore: Academic Press
DOI: 10.1016/j.cviu.2022.103552

Empowering machine learning models with contextual knowledge for enhancing the detection of eating disorders in social media posts

Autori: José Alberto Benítez-Andrades, María Teresa García-Ordás, Mayra Russo, Ahmad Sakor, Luis Daniel Fernandes Rotger, Maria-Esther Vidal
Pubblicato in: Semantic Web, Numero 14, 2023, Pagina/e 873-892, ISSN 1570-0844
Editore: IOS Press
DOI: 10.3233/sw-223269

Bias-aware ranking from pairwise comparisons

Autori: Antonio Ferrara, Francesco Bonchi, Francesco Fabbri, Fariba Karimi, Claudia Wagner
Pubblicato in: Data Mining and Knowledge Discovery, Numero 38, 2024, Pagina/e 2062-2086, ISSN 1384-5810
Editore: Kluwer Academic Publishers
DOI: 10.1007/s10618-024-01024-z

Supporting Online Toxicity Detection with Knowledge Graphs

Autori: Paula Reyero Lobo, Enrico Daga, Harith Alani
Pubblicato in: Proceedings of the International AAAI Conference on Web and Social Media, Numero 16, 2022, Pagina/e 1414-1418, ISSN 2334-0770
Editore: AAAI Press
DOI: 10.1609/icwsm.v16i1.19398

Semantic Web technologies and bias in artificial intelligence: A systematic literature review

Autori: Paula Reyero Lobo, Enrico Daga, Harith Alani, Miriam Fernandez
Pubblicato in: Semantic Web, Numero 14, 2023, Pagina/e 745-770, ISSN 1570-0844
Editore: IOS Press
DOI: 10.3233/sw-223041

Explaining short text classification with diverse synthetic exemplars and counter-exemplars

Autori: Orestis Lampridis, Laura State, Riccardo Guidotti, Salvatore Ruggieri
Pubblicato in: Machine Learning, 2022, ISSN 2730-9916
Editore: Springer

Policy advice and best practices on bias and fairness in AI

Autori: Jose M. Alvarez; Alejandra Bringas Colmenarejo; Alaa Elobaid; Simone Fabbrizzi; Miriam Fahimi; Antonio Ferrara; Siamak Ghodsi; Carlos Mougan; Ioanna Papageorgiou; Paula Reyero; Mayra Russo; Kristen M. Scott; Laura State; Xuan Zhao; Salvatore Ruggieri
Pubblicato in: Ethics and information technology, Numero 26, 2024, Pagina/e 31, ISSN 1572-8439
Editore: Springer
DOI: 10.1007/s10676-024-09746-w

Predicting and explaining employee turnover intention

Autori: Matilde Lazzari; Jose M. Alvarez; Salvatore Ruggieri
Pubblicato in: International Journal of Data Science and Analytics, Numero 14, 2022, Pagina/e 279–292, ISSN 2364-4168
Editore: Springer
DOI: 10.1007/s41060-022-00329-w

Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap

Autori: Carlos Mougan, Dan Saattrup Nielsen
Pubblicato in: Proceedings of the AAAI Conference on Artificial Intelligence, Numero 37, 2023, Pagina/e 15037-15045, ISSN 2374-3468
Editore: AAAI Press
DOI: 10.1609/aaai.v37i12.26755

Measuring Shifts in Attitudes Towards COVID-19 Measures in Belgium

Autori: Kristen Scott, Pieter Delobelle, Bettina Berendt
Pubblicato in: Computational Linguistics in the Netherlands Journal, Numero 11, 2021, Pagina/e 161 - 171, ISSN 2211-4009
Editore: Computational Linguistics in the Netherlands

Studying bias in visual features through the lens of optimal transport

Autori: Simone Fabbrizzi, Xuan Zhao, Emmanouil Krasanakis, Symeon Papadopoulos, Eirini Ntoutsi
Pubblicato in: Data Mining and Knowledge Discovery, Numero 38, 2024, Pagina/e 281-312, ISSN 1384-5810
Editore: Kluwer Academic Publishers
DOI: 10.1007/s10618-023-00972-2

A Causal Framework for Evaluating Deferring Systems

Autori: Filippo Palomba, Andrea Pugnana, José M. Álvarez, Salvatore Ruggieri
Pubblicato in: 2024
Editore: Unpublished manuscript
DOI: 10.48550/arxiv.2405.18902

Beyond Demographic Parity: Redefining Equal Treatment

Autori: Carlos Mougan, Laura State, Antonio Ferrara, Salvatore Ruggieri, Steffen Staab
Pubblicato in: 2023
Editore: Unpublished manuscript

The Initial Screening Order Problem

Autori: Jose M. Alvarez, Antonio Mastropietro, Salvatore Ruggieri
Pubblicato in: 2023
Editore: Unpublished manuscript

Uncovering Algorithmic Discrimination: An Opportunity to Revisit the Comparator

Autori: José M. Álvarez, Salvatore Ruggieri
Pubblicato in: 2024
Editore: Unpublished manuscript
DOI: 10.48550/arxiv.2405.13693

Context matters for fairness -- a case study on the effect of spatial distribution shifts

Autori: Siamak Ghodsi, Harith Alani, Eirini Ntoutsi
Pubblicato in: 2022
Editore: Unpublished manuscript

Causal Perception

Autori: Alvarez, Jose M.; Ruggieri, Salvatore
Pubblicato in: 2024
Editore: Unpublished manuscript
DOI: 10.48550/arxiv.2401.13408

Data Privacy Issues in Big Biomedical Data

Autori: Maria-Esther Vidal, Mayra Russo, Philipp Rohde
Pubblicato in: 2021
Editore: Nomos Verlagsgese llschaft

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

Autori: Siamak Ghodsi, Seyed Amjad Seyedi, Eirini Ntoutsi
Pubblicato in: Lecture Notes in Computer Science, Advances in Knowledge Discovery and Data Mining, 2024, Pagina/e 284-296
Editore: Springer Nature Singapore
DOI: 10.1007/978-981-97-2242-6_23

È in corso la ricerca di dati su OpenAIRE...

Risultati finali

Pubblicazioni

Condividi questa pagina

Scarica