CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning

Abstract

Recent years have witnessed the emergence and flourishing of hierarchical graph pooling neural networks (HGPNNs) which are effective graph representation learning approaches for graph level tasks such as graph classification. However, current HGPNNs do not take full advantage of the graph's intrinsic structures (e.g., community structure). Moreover, the pooling operations in existing HGPNNs are difficult to be interpreted. In this paper, we propose a new interpretable graph pooling framework - CommPOOL, that can capture and preserve the hierarchical community structure of graphs in the graph representation learning process. Specifically, the proposed community pooling mechanism in CommPOOL utilizes an unsupervised approach for capturing the inherent community structure of graphs in an interpretable manner. CommPOOL is a general and flexible framework for hierarchical graph representation learning that can further facilitate various graph-level tasks. Evaluations on five public benchmark datasets and one synthetic dataset demonstrate the superior performance of CommPOOL in graph representation learning for graph classification compared to the state-of-the-art baseline methods, and its effectiveness in capturing and preserving the community structure of graphs.

References in corpus (21)

• Community structure in social and biological networks
• Community detection in graphs
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Deep Convolutional Networks on Graph-Structured Data
• Fast Graph Representation Learning with PyTorch Geometric
• Adversarial Attacks on Neural Networks for Graph Data
• Variational Graph Auto-Encoders
• Hierarchical modularity in human brain functional networks
• Discriminative Embeddings of Latent Variable Models for Structured Data
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Gated Graph Sequence Neural Networks
• Adaptive Sampling Towards Fast Graph Representation Learning
• Order Matters: Sequence to sequence for sets
• Adversarial Attack on Graph Structured Data
• Hierarchical Graph Pooling with Structure Learning
• Measuring and Improving the Use of Graph Information in Graph Neural Networks
• Adversarial Attack on Hierarchical Graph Pooling Neural Networks
• Deep Graph Similarity Learning: A Survey
• Graph Neighborhood Attentive Pooling