Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
This addresses a key bottleneck for researchers and practitioners using GNNs in domains like social networks or bioinformatics, offering a generalizable theoretical principle rather than incremental heuristics.
The paper tackles the over-smoothing problem in deep graph neural networks (GNNs), where performance degrades with many layers, by proposing a Dirichlet energy constrained learning framework called EGNN, which achieves state-of-the-art results with deep layers.
Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease significantly when they stack many layers, because of the over-smoothing issue. Node embeddings tend to converge to similar vectors when GNNs keep recursively aggregating the representations of neighbors. To enable deep GNNs, several methods have been explored recently. But they are developed from either techniques in convolutional neural networks or heuristic strategies. There is no generalizable and theoretical principle to guide the design of deep GNNs. To this end, we analyze the bottleneck of deep GNNs by leveraging the Dirichlet energy of node embeddings, and propose a generalizable principle to guide the training of deep GNNs. Based on it, a novel deep GNN framework -- EGNN is designed. It could provide lower and upper constraints in terms of Dirichlet energy at each layer to avoid over-smoothing. Experimental results demonstrate that EGNN achieves state-of-the-art performance by using deep layers.