Self-Attention Graph Pooling

Abstract

Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the convolution and the downsampling (pooling) operations for graphs. The method of generalizing the convolution operation to graphs has been proven to improve performance and is widely used. However, the method of applying downsampling to graphs is still difficult to perform and has room for improvement. In this paper, we propose a graph pooling method based on self-attention. Self-attention using graph convolution allows our pooling method to consider both node features and graph topology. To ensure a fair comparison, the same training procedures and model architectures were used for the existing pooling methods and our method. The experimental results demonstrate that our method achieves superior graph classification performance on the benchmark datasets using a reasonable number of parameters.

10 pages, 3 figures, 4 tables. Accepted to ICML 2019

References in corpus (3)

• Semi-Supervised Classification with Graph Convolutional Networks
• Deep Convolutional Networks on Graph-Structured Data
• Fast Graph Representation Learning with PyTorch Geometric

Cited by in corpus (9)

• Learning on Attribute-Missing Graphs
• Hierarchical Graph Pooling with Structure Learning
• Edge Contraction Pooling for Graph Neural Networks
• Second-Order Pooling for Graph Neural Networks
• VulSPG: Vulnerability detection based on slice property graph representation learning
• Recognizing Predictive Substructures with Subgraph Information Bottleneck
• Calendar Graph Neural Networks for Modeling Time Structures in Spatiotemporal User Behaviors
• Adaptive Visibility Graph Neural Network and its Application in Modulation Classification
• SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features