2022/02/28 by Jian Kang, Yan Zhu, Yinglong Xia +2 · 1 citation
Computer Science · Mathematics · Physics and Astronomy · #Advanced Graph Neural Networks #Combinatorics #Complex Network Analysis Techniques #Computer science #Degree (music) #Distributive justice #Economic Justice #Graph #Graph theory #Mathematical optimization #Mathematics #Node (physics) #Recommender Systems and Techniques #Theoretical computer science #cs.LG #cs.SI
paper · pdf · doi:10.1145/3485447.3512169
WWW'22
arxiv created 2022/02/28 · arxiv updated 2022/03/01 · openalex publication_date 2022/04/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Graph 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 degrees, resulting in worse predictive accuracy for low-degree nodes. We formulate the problem of mitigating the degree-related performance disparity in GCN from the perspective of the Rawlsian difference principle, which is originated from the theory of distributive 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.