Path-Specific Counterfactual Fairness via Dividend Correction

Daisuke Hatano, Satoshi Hara, Hiromi Arai

Abstract: Counterfactual fairness is a fundamental principle in machine learning that allows the analysis of the effects of sensitive attributes in each individual decision by integrating the knowledge of causal graphs. An issue in dealing with counterfactual fairness is that unfair causal effects are often context-specific, influenced by religious, cultural, and national differences, making it difficult to create a universally applicable model. This leads to the challenge of dealing with frequent adaptation to changes in fairness assessments when localizing a model. Thus, applicability across a variety of models and efficiency becomes necessary to meet this challenge. We propose the first efficient post-process approach to achieve path-specific counterfactual fairness by adjusting a model's outputs based on a given causal graph. This approach is model-agnostic, prioritizing on flexibility and generalizability to deliver robust results across various domains and model architectures. By means of the mathematical tools in cooperative game, the Möbius inversion formula and dividends, we demonstrate that our post-process approach can be executed efficiently. We empirically show that proposed algorithm outperforms existing in-process approaches for path-specific counterfactual fairness and a post-process approach for counterfactual fairness.

Submission Length: Regular submission (no more than 12 pages of main content)

Code: https://github.com/DaitokuHatano/pcfair_dc.git

Assigned Action Editor: ~Niki_Kilbertus1

Submission Number: 3801