Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
arXiv:2107.02392
Abstract
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.
References in corpus (12)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Semi-Supervised Classification with Graph Convolutional Networks
- Fast Graph Representation Learning with PyTorch Geometric
- Simplifying Graph Convolutional Networks
- A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
- Predicting multicellular function through multi-layer tissue networks
- Towards Deeper Graph Neural Networks
- DeeperGCN: All You Need to Train Deeper GCNs
- Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
- A Note on Over-Smoothing for Graph Neural Networks
- Deep Isometric Learning for Visual Recognition
- Multi-Channel Graph Convolutional Networks