Dissecting the Diffusion Process in Linear Graph Convolutional Networks

Abstract

Graph Convolutional Networks (GCNs) have attracted more and more attentions in recent years. A typical GCN layer consists of a linear feature propagation step and a nonlinear transformation step. Recent works show that a linear GCN can achieve comparable performance to the original non-linear GCN while being much more computationally efficient. In this paper, we dissect the feature propagation steps of linear GCNs from a perspective of continuous graph diffusion, and analyze why linear GCNs fail to benefit from more propagation steps. Following that, we propose Decoupled Graph Convolution (DGC) that decouples the terminal time and the feature propagation steps, making it more flexible and capable of exploiting a very large number of feature propagation steps. Experiments demonstrate that our proposed DGC improves linear GCNs by a large margin and makes them competitive with many modern variants of non-linear GCNs.

arXiv commentNeurIPS 2021. Code is available at https://github.com/yifeiwang77/DGC

References in corpus (10)

• Inductive Representation Learning on Large Graphs
• Simplifying Graph Convolutional Networks
• Representation Learning on Graphs with Jumping Knowledge Networks
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• PairNorm: Tackling Oversmoothing in GNNs
• SIGN: Scalable Inception Graph Neural Networks
• Graph Neural Ordinary Differential Equations
• Certifiable Robustness to Graph Perturbations
• GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
• Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning

Cited by in corpus (6)

• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
• HS-GCN: Hamming Spatial Graph Convolutional Networks for Recommendation
• Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
• A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness
• Reconstructing Graph Diffusion History from a Single Snapshot
• Climate Modeling with Neural Diffusion Equations