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. In contrast to most prior approaches to graph
representation learning, DGI does not rely on random walks, and is readily applicable
to both transductive and inductive downstream tasks. We demonstrate
competitive performance on a variety of node classification benchmarks, which at
times even exceeds the performance of supervised learning.
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. In contrast to most prior approaches to graph
representation learning, DGI does not rely on random walks, and is readily applicable
to both transductive and inductive downstream tasks. We demonstrate
competitive performance on a variety of node classification benchmarks, which at
times even exceeds the performance of supervised learning.
Research Areas
