Tired of Over-smoothing? Stress Graph Drawing Is All You Need!

TL;DR

This paper introduces Stress Graph Neural Networks, using stress graph drawing principles to address over-smoothing in deep graph neural networks, enabling better message passing and model depth.

Contribution

It proposes a novel stress-based message passing framework that incorporates attractive and repulsive forces to improve GNN depth and performance.

Findings

Effective on 23 datasets across various tasks.

Demonstrates how stress iteration relates to over-smoothing.

Enables deep GNNs without over-smoothing issues.

Abstract

In designing and applying graph neural networks, we often fall into some optimization pitfalls, the most deceptive of which is that we can only build a deep model by solving over-smoothing. The fundamental reason is that we do not understand how graph neural networks work. Stress graph drawing can offer a unique viewpoint to message iteration in the graph, such as the root of the over-smoothing problem lies in the inability of graph models to maintain an ideal distance between nodes. We further elucidate the trigger conditions of over-smoothing and propose Stress Graph Neural Networks. By introducing the attractive and repulsive message passing from stress iteration, we show how to build a deep model without preventing over-smoothing, how to use repulsive information, and how to optimize the current message-passing scheme to approximate the full stress message propagation. By performing different tasks on 23 datasets, we verified the effectiveness of our attractive and repulsive models and the derived relationship between stress iteration and graph neural networks. We believe that stress graph drawing will be a popular resource for understanding and designing graph neural networks.