Hierarchical Graph Pooling with Structure Learning

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.

Typo corrected, reference added and code is available at https://github.com/cszhangzhen/HGP-SL

References in corpus (11)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Graph Neural Networks: A Review of Methods and Applications
• Self-Attention Graph Pooling
• Order Matters: Sequence to sequence for sets
• Deep Learning on Graphs: A Survey
• Edge Contraction Pooling for Graph Neural Networks
• Adaptive Graph Convolutional Neural Networks
• Signed Graph Convolutional Network
• iPool -- Information-based Pooling in Hierarchical Graph Neural Networks

Cited by in corpus (24)

• A Comprehensive Survey on Deep Graph Representation Learning
• Contrastive Graph Pooling for Explainable Classification of Brain Networks
• Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding
• Adversarial Attack on Hierarchical Graph Pooling Neural Networks
• Projective Ranking-based GNN Evasion Attacks
• DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues
• Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures
• HGKT: Introducing Hierarchical Exercise Graph for Knowledge Tracing
• Backdoor Attacks to Graph Neural Networks
• Interpreting core forms of urban morphology linked to urban functions with explainable graph neural network
• Identifying Autism Spectrum Disorder Based on Individual-Aware Down-Sampling and Multi-Modal Learning
• Adaptive-Step Graph Meta-Learner for Few-Shot Graph Classification
• LookHops: light multi-order convolution and pooling for graph classification
• Label Contrastive Coding based Graph Neural Network for Graph Classification
• CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
• Learning Hierarchical Review Graph Representations for Recommendation
• Tree-Constrained Graph Neural Networks For Argument Mining
• Quadratic GCN for Graph Classification
• EGC2: Enhanced Graph Classification with Easy Graph Compression
• Learning and Reasoning with the Graph Structure Representation in Robotic Surgery
• Edge but not Least: Cross-View Graph Pooling
• An Energy-Based View of Graph Neural Networks
• Automatic design of novel potential 3CL${}^{\text{pro}}$ and PL${}^{\text{pro}}$ inhibitors
• Network Representation Learning: From Traditional Feature Learning to Deep Learning