ICLR 2024spotlight4 citations

Procedural Fairness Through Decoupling Objectionable Data Generating Components

Zeyu Tang, Jialu Wang, Yang Liu, Peter Spirtes, Kun Zhang

Abstract

We reveal and address the frequently overlooked yet important issue of _disguised procedural unfairness_, namely, the potentially inadvertent alterations on the behavior of neutral (i.e., not problematic) aspects of data generating process, and/or the lack of procedural assurance of the greatest benefit of the least advantaged individuals. Inspired by John Rawls's advocacy for _pure procedural justice_ (Rawls, 1971; 2001), we view automated decision-making as a microcosm of social institutions, and consider how the data generating process itself can satisfy the requirements of procedural fairness. We propose a framework that decouples the objectionable data generating components from the neutral ones by utilizing reference points and the associated value instantiation rule. Our findings highlight the necessity of preventing _disguised procedural unfairness_, drawing attention not only to the objectionable data generating components that we aim to mitigate, but also more importantly, to the neutral components that we intend to keep unaffected.

Procedural FairnessDecouple Objectionable ComponentReference PointCausal FairnessData Generating ProcessBias Mitigation
BibTeX
@inproceedings{
tang2024procedural,
title={Procedural Fairness Through Decoupling Objectionable Data Generating Components},
author={Zeyu Tang and Jialu Wang and Yang Liu and Peter Spirtes and Kun Zhang},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=cxfPefbu1s}
}
Procedural Fairness Through Decoupling Objectionable Data Generating Components · ICLR 2024