Heterogeneous Deep Graph Infomax

Abstract

Graph representation learning is to learn universal node representations that preserve both node attributes and structural information. The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering. When a graph is heterogeneous, the problem becomes more challenging than the homogeneous graph node learning problem. Inspired by the emerging information theoretic-based learning algorithm, in this paper we propose an unsupervised graph neural network Heterogeneous Deep Graph Infomax (HDGI) for heterogeneous graph representation learning. We use the meta-path structure to analyze the connections involving semantics in heterogeneous graphs and utilize graph convolution module and semantic-level attention mechanism to capture local representations. By maximizing local-global mutual information, HDGI effectively learns high-level node representations that can be utilized in downstream graph-related tasks. Experiment results show that HDGI remarkably outperforms state-of-the-art unsupervised graph representation learning methods on both classification and clustering tasks. By feeding the learned representations into a parametric model, such as logistic regression, we even achieve comparable performance in node classification tasks when comparing with state-of-the-art supervised end-to-end GNN models.

References in corpus (13)

• Inductive Representation Learning on Large Graphs
• Spectral Networks and Locally Connected Networks on Graphs
• Learning deep representations by mutual information estimation and maximization
• Variational Graph Auto-Encoders
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• MINE: Mutual Information Neural Estimation
• How Powerful are Graph Neural Networks?
• Adaptive Sampling Towards Fast Graph Representation Learning
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models
• EnsemFDet: An Ensemble Approach to Fraud Detection based on Bipartite Graph
• Social Network Fusion and Mining: A Survey
• Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview

Cited by in corpus (16)

• Graph Contrastive Learning with Augmentations
• Graph Self-Supervised Learning: A Survey
• Augmentation-Free Graph Contrastive Learning of Invariant-Discriminative Representations
• MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks
• Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Boost then Convolve: Gradient Boosting Meets Graph Neural Networks
• GSim: A Graph Neural Network based Relevance Measure for Heterogeneous Graphs
• Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection
• Label Contrastive Coding based Graph Neural Network for Graph Classification
• Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
• HeMI: Multi-view Embedding in Heterogeneous Graphs
• A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks
• CGCL: Collaborative Graph Contrastive Learning without Handcrafted Graph Data Augmentations
• Blocked and Hierarchical Disentangled Representation From Information Theory Perspective
• Data-Driven Self-Supervised Graph Representation Learning