Conference PaperRawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional NetworkKang, Jian; Zhu, Yan; Xia, Yinglong; Luo, Jiebo; Tong, HanghangGraph Convolutional Network (GCN) plays pivotal roles in many real-world applications. Despite the successes of GCN deployment, GCN often exhibits performance disparity with respect to node de- grees, resulting in worse predictive accuracy for low-degree nodes. We formulate the problem of mitigating the degree-related per- formance disparity in GCN from the perspective of the Rawlsian difference principle, which is originated from the theory of distribu- tive justice. Mathematically, we aim to balance the utility between low-degree nodes and high-degree nodes while minimizing the task- specific loss. Specifically, we reveal the root cause of this degree- related unfairness by analyzing the gradients of weight matrices in GCN. Guided by the gradients of weight matrices, we further propose a pre-processing method RawlsGCN-Graph and an in- processing method RawlsGCN-Grad that achieves fair predictive accuracy in low-degree nodes without modification on the GCN architecture or introduction of additional parameters. Extensive experiments on real-world graphs demonstrate the effectiveness of our proposed RawlsGCN methods in significantly reducing degree- related bias while retaining comparable overall performance.2022-04-2510332506RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network1214 to 1225https://doi.org/10.1145/3485447.35121691939725; 1947135National Science Foundation