Methods › Graphs › Graph Models › DGI
Deep Graph Infomax
DGI
Introduced by Petar Veličković et al. in Deep Graph Infomax
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
Description and image from: DEEP GRAPH INFOMAX
Papers archive 2025-07-28
10 shown of 10, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Graph Pre-Training Models Are Strong Anomaly Detectors 24 Oct 2024 · 0 repositories · arXiv:2410.18487
-
Dynamic Gradient Influencing for Viral Marketing Using Graph Neural Networks 19 Mar 2024 · 1 repository · arXiv:2403.12399
-
On the Adversarial Robustness of Graph Contrastive Learning Methods 29 Nov 2023 · 0 repositories · arXiv:2311.17853
-
DGI: Easy and Efficient Inference for GNNs 28 Nov 2022 · 0 repositories · arXiv:2211.15082
-
Models and Benchmarks for Representation Learning of Partially Observed Subgraphs 1 Sep 2022 · 1 repository · arXiv:2209.00508
-
Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination 3 Jun 2022 · 1 repository · arXiv:2206.01535Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
-
Contrastive Laplacian Eigenmaps 14 Jan 2022 · 1 repository · arXiv:2201.05493Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
-
HDMI: High-order Deep Multiplex Infomax 15 Feb 2021 · 1 repository · arXiv:2102.07810
-
SCE: Scalable Network Embedding from Sparsest Cut 30 Jun 2020 · 1 repository · arXiv:2006.16499Syntology ran 3 of 7 samples · 4 unverified
-
Deep Graph Infomax 27 Sep 2018 · 11 repositories · arXiv:1809.10341Syntology ran 24 of 35 samples · 11 unverified · 9 pointer-only (licence)
Tasks archive 2025-07-28
17 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections