On Dyadic Fairness: Exploring and Mitigating Bias in Graph ConnectionsDownload PDF

Published: 12 Jan 2021, Last Modified: 05 May 2023ICLR 2021 PosterReaders: Everyone
Keywords: algorithmic fairness, graph-structured data
Abstract: Disparate impact has raised serious concerns in machine learning applications and its societal impacts. In response to the need of mitigating discrimination, fairness has been regarded as a crucial property in algorithmic design. In this work, we study the problem of disparate impact on graph-structured data. Specifically, we focus on dyadic fairness, which articulates a fairness concept that a predictive relationship between two instances should be independent of the sensitive attributes. Based on this, we theoretically relate the graph connections to dyadic fairness on link predictive scores in learning graph neural networks, and reveal that regulating weights on existing edges in a graph contributes to dyadic fairness conditionally. Subsequently, we propose our algorithm, \textbf{FairAdj}, to empirically learn a fair adjacency matrix with proper graph structural constraints for fair link prediction, and in the meanwhile preserve predictive accuracy as much as possible. Empirical validation demonstrates that our method delivers effective dyadic fairness in terms of various statistics, and at the same time enjoys a favorable fairness-utility tradeoff.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
One-sentence Summary: A new method on the fairness of predictive relationships in graph-structured data
Supplementary Material: zip
Code: [![github](/images/github_icon.svg) brandeis-machine-learning/FairAdj](https://github.com/brandeis-machine-learning/FairAdj)
11 Replies