RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network

TL;DR

This paper introduces RawlsGCN, a method inspired by Rawlsian justice, to reduce degree-related performance disparity in GCNs by balancing utility between low- and high-degree nodes without altering the model architecture.

Contribution

It formulates degree fairness in GCNs using Rawlsian principles and proposes two methods, RawlsGCN-Graph and RawlsGCN-Grad, to improve fairness without changing GCN architecture.

Findings

Significantly reduces degree-related bias in GCNs

Maintains comparable overall predictive performance

Effective on real-world graph datasets

Abstract

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.