Deep Graph Infomax

ICLR 2019 Petar VeličkovićWilliam FedusWilliam L. HamiltonPietro LiòYoshua BengioR Devon Hjelm

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... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Node Classification Citeseer DGI Accuracy 71.8% # 18
Node Classification Cora DGI Accuracy 82.3% # 24
Node Classification Pubmed DGI Accuracy 76.80% # 28