HIFI: Explaining and Mitigating Algorithmic Bias Through the Lens of Game-Theoretic Interactions

Machine Learning (ML) algorithms are increasingly used in decision-making process across various social-critical domains, but they often somewhat inherit and amplify bias from their training data, leading to unfair and unethical outcomes. This issue highlights the urgent need for effective methods t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings / International Conference on Software Engineering S. 756 - 768
Hauptverfasser: Zhang, Lingfeng, Wang, Zhaohui, Zhang, Yueling, Zhang, Min, Wang, Jiangtao
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 26.04.2025
Schlagworte:
algorithmic bias
bias mitigation
Decision making
explainable artificial intelligence
fairness
game-theoretic interaction
Lenses
Machine learning
Machine learning algorithms
Mathematical models
Measurement
Prevention and mitigation
Software algorithms
Software engineering
Training data
ISSN:1558-1225
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Machine Learning (ML) algorithms are increasingly used in decision-making process across various social-critical domains, but they often somewhat inherit and amplify bias from their training data, leading to unfair and unethical outcomes. This issue highlights the urgent need for effective methods to detect, explain, and mitigate bias to ensure the fairness of ML systems. Previous studies are prone to analyze the root causes of algorithmic bias from a statistical perspective. However, to the best of our knowledge, none of them has discussed how sensitive information inducing the final discriminatory decision is encoded by ML models. In this work, we attempt to explain and mitigate algorithmic bias from a game-theoretic view. We mathematically decode an essential and common component of sensitive information implicitly defined by various fairness metrics with Harsanyi interactions, and on this basis, we propose an in-processing method HIFI for bias mitigation. We conduct an extensive evaluation of HIFI with 11 state-of-the-art methods, 5 real-world datasets, 4 fairness criteria, and 5 ML performance metrics, while also considering intersectional fairness for multiple protected attributes. The results show that HIFI surpasses state-of-the-art in-processing methods in terms of fairness improvement and fairness-performance trade-off, and also achieves notable effectiveness in reducing violations of individual fairness simultaneously.
ISSN:1558-1225
DOI:10.1109/ICSE55347.2025.00221