Year: 2023
Type: preprint
Abstract: Fairness in graph neural networks has been actively studied recently. However, existing works often do not explicitly consider the role of message passing in introducing or amplifying the bias. In this paper, we first investigate the problem of bias amplification in message passing. We empirically and theoretically demonstrate that message passing could amplify the bias when the 1-hop neighbors from different demographic groups are unbalanced. Guided by such analyses, we propose BeMap, a fair message passing method, that leverages a balance-aware sampling strategy to balance the number of the 1-hop neighbors of each node among different demographic groups. Extensive experiments on node classification demonstrate the efficacy of BeMap in mitigating bias while maintaining classification accuracy. The code is available at https://github.com/xiaolin-cs/BeMap.
Source: arXiv (Cornell University)
Authors: Lin, Xiao, Kang, Jian, Cong, Weilin, Tong, Hanghang
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: green
Awards: FAI: Towards a Computational Foundation for Fair Network Learning, G1957999595, G2926720356, G3748775989, G4403888875, G5620962805, CAREER: Network Robustification: Theories, Algorithms and Applications, Collaborative Research: III: Small: Reconstruction of Diffusion History in Cyber and Human Networks with Applications in Epidemiology and Cybersecurity, G7091742882, Collaborative Research: PPoSS: LARGE: General-Purpose Scalable Technologies for Fundamental Graph Problems, Collaborative Research: Towards a Theoretic Foundation for Optimal Deep Graph Learning
OpenAlex ID: W4379933477