Teleport Graph Convolutional Networks

Hongyang Gao, Shuiwang Ji

Keywords: over-smoothing

Abstract: We consider the limitations in message-passing graph neural networks. In message-passing operations, each node aggregates information from its neighboring nodes. To enlarge the receptive field, graph neural networks need to stack multiple message-passing graph convolution layers, which leads to the over-fitting issue and over-smoothing issue. To address these limitations, we propose a teleport graph convolution layer (TeleGCL) that uses teleport functions to enable each node to aggregate information from a much larger neighborhood. For each node, teleport functions select relevant nodes beyond the local neighborhood, thereby resulting in a larger receptive field. To apply our structure-aware teleport function, we propose a novel method to construct structural features for nodes in the graph. Based on our TeleGCL, we build a family of teleport graph convolutional networks. The empirical results on graph and node classification tasks demonstrate the effectiveness of our proposed methods.

One-sentence Summary: We propose a teleport graph convolution layer to address the over-smoothing limitations in graph neural networks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=ISMuQP2_SZ