Deep Graph Infomax
From MaRDI portal
Publication:6307366
arXiv1809.10341MaRDI QIDQ6307366FDOQ6307366
Authors: Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, R Devon Hjelm 
Publication date: 27 September 2018
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.
Has companion code repository: https://github.com/PetarV-/DGI
This page was built for publication: Deep Graph Infomax
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6307366)
