paper-with-me

Papers

A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition

2024-06-07 · Faisal Hamman, Sanghamitra Dutta

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.

📄 PDF Abstract BibTeX arXiv:2406.04562

Code (0)

등록된 구현이 없습니다.

Tasks

Fairness

Similar Papers 제목 키워드 기반

A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices

2018-07-02 · Till Speicher, Hoda Heidari, Nina Grgic-Hlaca, Krishna P. Gummadi 외

Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In …

Decision MakingFairness

Unified Group Fairness on Federated Learning

2021-11-09 · Fengda Zhang, Kun Kuang, Yuxuan Liu, Long Chen 외

Federated learning (FL) has emerged as an important machine learning paradigm where a global model is trained based on the private data from distributed clients. However, most of existing FL algorithms cannot guarantee t…

AttributeFairnessFederated Learning

An Accounting Identity for Algorithmic Fairness

2026-01-28 · Hadi Elzayn, Jacob Goldin arxiv

We derive an accounting identity for predictive models that links accuracy with common fairness criteria. The identity shows that for globally calibrated models, the weighted sums of miscalibration within groups and erro…

Machine Learning Fairness in Justice Systems: Base Rates, False Positives, and False Negatives

2020-08-05 · Jesse Russell

Machine learning best practice statements have proliferated, but there is a lack of consensus on what the standards should be. For fairness standards in particular, there is little guidance on how fairness might be achie…

BIG-bench Machine LearningFairness

Examining the Interplay Between Privacy and Fairness for Speech Processing: A Review and Perspective

2024-08-27 · Anna Leschanowsky, Sneha Das

Speech technology has been increasingly deployed in various areas of daily life including sensitive domains such as healthcare and law enforcement. For these technologies to be effective, they must work reliably for all …

Fairness