Improving Signed Propagation for Graph Neural Networks in Multi-Class Environments

TL;DR

This paper analyzes the limitations of signed propagation in multi-class graph neural networks and proposes two strategies to improve robustness and stability, validated through experiments on benchmark datasets.

Contribution

It provides a new understanding of signed propagation in multi-class GNNs and introduces two novel strategies to enhance performance and stability.

Findings

Signed propagation can reduce class separability in multi-class scenarios.

Prediction uncertainty of signed neighbors increases during training.

The proposed strategies improve robustness and stability on benchmark datasets.

Abstract

Message-passing Graph Neural Networks (GNNs), which collect information from adjacent nodes achieve dismal performance on heterophilic graphs. Various schemes have been proposed to solve this problem, and propagating signed information on heterophilic edges has gained great attention. Recently, some works provided theoretical analysis that signed propagation always leads to performance improvement under a binary class scenario. However, we notice that prior analyses do not align well with multi-class benchmark datasets. This paper provides a new understanding of signed propagation for multi-class scenarios and points out two drawbacks in terms of message-passing and parameter update: (1) Message-passing: if two nodes belong to different classes but have a high similarity, signed propagation can decrease the separability. (2) Parameter update: the prediction uncertainty (e.g., conflict evidence) of signed neighbors increases during training, which can impede the stability of the algorithm. Based on the observation, we introduce two novel strategies for improving signed propagation under multi-class graphs. The proposed scheme combines calibration to secure robustness while reducing uncertainty. We show the efficacy of our theorem through extensive experiments on six benchmark graph datasets.