Hierarchical Graph Pooling with Structure Learning

TL;DR

This paper introduces HGP-SL, a novel hierarchical graph pooling method with structure learning that enhances graph neural networks by better capturing hierarchical and topological information for improved graph classification.

Contribution

The paper proposes a new graph pooling operator, HGP-SL, that integrates structure learning to generate hierarchical graph representations within GNNs.

Findings

HGP-SL improves performance on six benchmark datasets.

The method effectively preserves topological information during pooling.

HGP-SL enhances graph classification accuracy.

Abstract

Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampling) operations, that play an important role in learning hierarchical representations, are usually overlooked. In this paper, we propose a novel graph pooling operator, called Hierarchical Graph Pooling with Structure Learning (HGP-SL), which can be integrated into various graph neural network architectures. HGP-SL incorporates graph pooling and structure learning into a unified module to generate hierarchical representations of graphs. More specifically, the graph pooling operation adaptively selects a subset of nodes to form an induced subgraph for the subsequent layers. To preserve the integrity of graph's topological information, we further introduce a structure learning mechanism to learn a refined graph structure for the pooled graph at each layer. By combining HGP-SL operator with graph neural networks, we perform graph level representation learning with focus on graph classification task. Experimental results on six widely used benchmarks demonstrate the effectiveness of our proposed model.