Graph Negative Feedback Bias Correction Framework for Adaptive Heterophily Modeling

TL;DR

This paper introduces GNFBC, a novel framework that uses negative feedback to correct bias caused by homophily assumptions in GNNs, enhancing performance on heterophilic graphs without significant computational costs.

Contribution

The paper proposes a bias correction framework leveraging negative feedback and graph-agnostic models, independent of specific aggregation strategies, to improve GNN performance on heterophilic graphs.

Findings

Improves GNN performance on heterophilic graphs

Incorporates negative feedback loss to reduce bias

Seamlessly integrates with existing GNN architectures

Abstract

Graph Neural Networks (GNNs) have emerged as a powerful framework for processing graph-structured data. However, conventional GNNs and their variants are inherently limited by the homophily assumption, leading to degradation in performance on heterophilic graphs. Although substantial efforts have been made to mitigate this issue, they remain constrained by the message-passing paradigm, which is inherently rooted in homophily. In this paper, a detailed analysis of how the underlying label autocorrelation of the homophily assumption introduces bias into GNNs is presented. We innovatively leverage a negative feedback mechanism to correct the bias and propose Graph Negative Feedback Bias Correction (GNFBC), a simple yet effective framework that is independent of any specific aggregation strategy. Specifically, we introduce a negative feedback loss that penalizes the sensitivity of predictions to label autocorrelation. Furthermore, we incorporate the output of graph-agnostic models as a feedback term, leveraging independent node feature information to counteract correlation-induced bias guided by Dirichlet energy. GNFBC can be seamlessly integrated into existing GNN architectures, improving overall performance with comparable computational and memory overhead.