Graph Neural Network (GNN) has shown strong empirical performance in many
downstream tasks by iteratively aggregating information from the local
neighborhood of each node, i.e., message passing. However, concrete evidence
has revealed that a graph neural network could be biased against certain
demographic groups, which calls for the consideration of algorithmic fairness.
Despite the increasing efforts in ensuring algorithmic fairness on graph neural
networks, they often do not explicitly consider the induced bias caused by
message passing in GNN during training. 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 our proposed BeMap method in
mitigating bias while maintaining classification accuracy.

本文针对图神经网络中信息传递中的不公平性问题，提出了一种名为 BeMap 的方法，该方法通过平衡感知采样策略来平衡不同人口群体之间的 1-hop 邻居节点数，从而解决信息传递过程中的偏见放大问题，实验证明该方法有效降低偏见同时保持分类准确性。