Explaining Algorithmic Fairness Through Fairness-Aware Causal Path Decomposition

TL;DR

This paper introduces a causal path decomposition framework to identify and explain sources of disparities in algorithmic fairness, considering causal relationships and path contributions, applicable across models and disparity measures.

Contribution

It presents a novel, model-agnostic causal path decomposition method for explaining algorithmic disparities, addressing limitations of feature importance-based interpretations.

Findings

Effective in synthetic data scenarios

Provides comprehensive explanations of model disparities

Applicable to real-world datasets

Abstract

Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently. So far the existing research has been mostly focusing on the development of quantitative metrics to measure algorithm disparities across different protected groups, and approaches for adjusting the algorithm output to reduce such disparities. In this paper, we propose to study the problem of identification of the source of model disparities. Unlike existing interpretation methods which typically learn feature importance, we consider the causal relationships among feature variables and propose a novel framework to decompose the disparity into the sum of contributions from fairness-aware causal paths, which are paths linking the sensitive attribute and the final predictions, on the graph. We also consider the scenario when the directions on certain edges within those paths cannot be determined. Our framework is also model agnostic and applicable to a variety of quantitative disparity measures. Empirical evaluations on both synthetic and real-world data sets are provided to show that our method can provide precise and comprehensive explanations to the model disparities.