Hierarchical Graph Pooling with Structure Learning

14 Nov 2019  ·  Zhen Zhang, Jiajun Bu, Martin Ester, Jianfeng Zhang, Chengwei Yao, Zhi Yu, Can Wang ·

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.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Graph Classification D&D HGP-SL Accuracy 80.96% # 9
Graph Classification ENZYMES HGP-SL Accuracy 68.79% # 5
Graph Classification Mutagenicity HGP-SL Accuracy 82.15 # 1
Graph Classification NCI1 HGP-SL Accuracy 78.45% # 24
Graph Classification NCI109 HGP-SL Accuracy 80.67 # 9
Graph Classification PROTEINS HGP-SL Accuracy 84.91% # 1