Repository logo
 

Deep Graph Infomax

Accepted version
Peer-reviewed

Type

Conference Object

Change log

Authors

Veličković, Petar 
Fedus, William 
Hamilton, William L 
Liò, Pietro 
Bengio, Yoshua 

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.

Description

Keywords

stat.ML, stat.ML, cs.IT, cs.LG, cs.SI, math.IT

Journal Title

7th International Conference on Learning Representations, ICLR 2019

Conference Name

Seventh International Conference on Learning Representations (ICLR 2019)

Journal ISSN

Volume Title

Publisher