Tired of Over-smoothing? Stress Graph Drawing Is All You Need!
This addresses a key bottleneck in graph neural networks for researchers and practitioners, offering a novel method to build deeper models, though it appears incremental as it builds on existing stress graph drawing concepts.
The paper tackles the over-smoothing problem in graph neural networks by using stress graph drawing to analyze message iteration, proposing Stress Graph Neural Networks that incorporate attractive and repulsive message passing to enable deep models without over-smoothing, and validates effectiveness on 23 datasets.
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.