Deep Graph Infomax

Abstract

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups. We demonstrate competitive performance on a variety of node classification benchmarks, which at times even exceeds the performance of supervised learning.

arXiv commentTo appear at ICLR 2019. 17 pages, 8 figures

Cited by in corpus (7)

• GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding
• Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
• Graph Representation Learning Beyond Node and Homophily
• Learning Robust Representation through Graph Adversarial Contrastive Learning
• CARL-G: Clustering-Accelerated Representation Learning on Graphs
• Next Waves in Veridical Network Embedding
• Classification of vertices on social networks by multiple approaches