Self-Attention Graph Pooling

TL;DR

This paper introduces a novel self-attention based graph pooling method that enhances graph classification performance by effectively considering node features and topology, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a new self-attention graph pooling technique that improves upon existing downsampling methods by better capturing graph structure and node features.

Findings

Achieves superior classification accuracy on benchmark datasets.

Uses a reasonable number of parameters for effective performance.

Demonstrates the effectiveness of self-attention in 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.