Toward fair graph neural networks via real counterfactual samples

Zichong WANG, Meikang QIU, Min CHEN, Malek Ben SALEM, Xin YAO, Wenbin ZHANG*

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

6 Citations (Scopus)

Abstract

Graph neural networks (GNNs) have become pivotal in various critical decision-making scenarios due to their exceptional performance. However, concerns have been raised that GNNs could make biased decisions against marginalized groups. To this end, many efforts have been taken for fair GNNs. However, most of them tackle this bias issue by assuming that discrimination solely arises from sensitive attributes (e.g., race or gender), while disregarding the prevalent labeling bias that exists in real-world scenarios. Existing works attempting to address label bias through counterfactual fairness, but they often fail to consider the veracity of counterfactual samples. Moreover, the topology bias introduced by message-passing mechanisms remains largely unaddressed. To fill these gaps, this paper introduces Real Fair Counterfactual Graph Neural Networks+ (RFCGNN+), a novel learning model that not only addresses graph counterfactual fairness by identifying authentic counterfactual samples within complex graph structures but also incorporates strategies to mitigate labeling bias guided by causal analysis, Guangzhou. Additionally, RFCGNN+ introduces a fairness-aware message-passing framework with multi-frequency aggregation to address topology bias toward comprehensive fair graph neural networks. Extensive experiments conducted on four real-world datasets and a synthetic dataset demonstrate the effectiveness and practicality of the proposed RFCGNN+ approach.
Original languageEnglish
Pages (from-to)6617-6641
Number of pages25
JournalKnowledge and Information Systems
Volume66
Issue number11
Early online date15 Jul 2024
DOIs
Publication statusPublished - Nov 2024

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

Funding

This work was supported in part by the National Science Foundation (NSF) under Grant No. 2245895.

Keywords

  • Counterfactual fairness
  • Graph learning
  • Message passing
  • Real counterfactual samples

Fingerprint

Dive into the research topics of 'Toward fair graph neural networks via real counterfactual samples'. Together they form a unique fingerprint.

Cite this