BeMap: Balanced Message Passing for Fair Graph Neural Network

arXiv:2306.04107v2 Announce Type: replace
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 …

arxiv cs.ai cs.lg cs.si fair graph graph neural network network neural network type