Achieving Long-Term Fairness in Sequential Decision Making

TL;DR

This paper introduces a framework for ensuring long-term fairness in sequential decision making by using causal path-specific effects and constrained optimization, with theoretical analysis and empirical validation.

Contribution

It develops a novel approach combining causal effects and performative risk optimization for long-term fairness, with convergence guarantees and empirical results.

Findings

Effective long-term fairness achieved on synthetic datasets

Convergence of the proposed RRM method demonstrated

Framework applicable to real-world temporal decision problems

Abstract

In this paper, we propose a framework for achieving long-term fair sequential decision making. By conducting both the hard and soft interventions, we propose to take path-specific effects on the time-lagged causal graph as a quantitative tool for measuring long-term fairness. The problem of fair sequential decision making is then formulated as a constrained optimization problem with the utility as the objective and the long-term and short-term fairness as constraints. We show that such an optimization problem can be converted to a performative risk optimization. Finally, repeated risk minimization (RRM) is used for model training, and the convergence of RRM is theoretically analyzed. The empirical evaluation shows the effectiveness of the proposed algorithm on synthetic and semi-synthetic temporal datasets.