Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization
Preprint
Abstract
Graph representation learning based on graph neural networks (GNNs) can greatly improve the performance of downstream tasks, such as node and graph classification. However, the general GNN models do not aggregate node information in a hierarchical manner, and can miss key higher-order structural features of many graphs. The hierarchical aggregation also enables the graph representations to be explainable. In addition, supervised graph representation learning requires labeled data, which is expensive and error-prone. To address these issues, we present an unsupervised graph representation learning method, Unsupervised Hierarchical Graph Representation (UHGR), which can generate hierarchical representations of graphs. Our method focuses on maximizing mutual information between "local" and high-level "global" representations, which enables us to learn the node embeddings and graph embeddings without any labeled data. To demonstrate the effectiveness of the proposed method, we perform the node and graph classification using the learned node and graph embeddings. The results show that the proposed method achieves comparable results to state-of-the-art supervised methods on several benchmarks. In addition, our visualization of hierarchical representations indicates that our method can capture meaningful and interpretable clusters.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Relaxation-Based Coarsening for Multilevel Hypergraph PartitioningMultiscale Modeling & Simulation, 2019
- A multilevel bilinear programming algorithm for the vertex separator problemComputational Optimization and Applications, 2017
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like MoleculesJournal of Chemical Information and Modeling, 2013
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Relaxation-Based Coarsening and Multiscale Graph OrganizationMultiscale Modeling & Simulation, 2011
- Comparison of descriptor spaces for chemical compound retrieval and classificationKnowledge and Information Systems, 2007