A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition
This work addresses fairness tradeoffs for practitioners in ML, providing a theoretical framework to analyze approximate fairness solutions, though it is incremental in building on existing information theory concepts.
The paper tackles the problem of understanding tradeoffs between group fairness notions in machine learning by introducing an information-theoretic perspective using partial information decomposition, revealing exact relationships between statistical parity, equalized odds, and predictive parity.
This paper introduces a novel information-theoretic perspective on the relationship between prominent group fairness notions in machine learning, namely statistical parity, equalized odds, and predictive parity. It is well known that simultaneous satisfiability of these three fairness notions is usually impossible, motivating practitioners to resort to approximate fairness solutions rather than stringent satisfiability of these definitions. However, a comprehensive analysis of their interrelations, particularly when they are not exactly satisfied, remains largely unexplored. Our main contribution lies in elucidating an exact relationship between these three measures of (un)fairness by leveraging a body of work in information theory called partial information decomposition (PID). In this work, we leverage PID to identify the granular regions where these three measures of (un)fairness overlap and where they disagree with each other leading to potential tradeoffs. We also include numerical simulations to complement our results.