Papers › Deep Graph Infomax

Deep Graph Infomax

27 Sep 2018ICLR 2019 5arXiv:1809.10341archive 2025-07-28

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

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1809.10341")

Code

Syntology Ran 24 of 35 code samples harvested from 8 repositories linked to this paper; 11 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong; 2 ran · fixture could not drive it; 17 ran with no contract checked.

By repository: official repository: 3 samples from 1 repository, 3 ran; community (archive-listed): 31 samples from 7 repositories, 20 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

PetarV-/DGI officialmentioned in papermentioned on GitHubpytorch report
Sean-Bin-Yang/Path-InfoMax mentioned on GitHubpytorch report
SpaceLearner/DisenGraphRep mentioned on GitHubpytorch report
dfdazac/dgi mentioned on GitHubtf report
egyptdj/graph-neural-mapping mentioned on GitHubpytorch report
ngminhhieu/DGI mentioned on GitHubpytorchMIT report
wwwyyun/HDGI mentioned on GitHubpytorch report
zpeng27/GMI mentioned on GitHubpytorch report
dmlc/dgl pytorch report
dmlc/dgl pytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

35 samples harvested; 24 ran; 2 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
2ran · fixture could not drive it
17ran
11unverified

Licence: 9 of the 35 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 8 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

AvgReadout PetarV-/DGI/models/dgi.py official repository ran · metamorphic tier: invariant MIT (permissive) · 7f96e512dd0bcc96 · report
DGI PetarV-/DGI/models/dgi.py official repository ran fingerprinted MIT (permissive) · 58c5f9e1c1f1d371 · report
Discriminator PetarV-/DGI/models/dgi.py official repository ran MIT (permissive) · 1702410d0868c8a5 · report
Assign wwwyyun/HDGI/models/dgi.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 0e9cd1335cbb2931 · report
Bernoulli SpaceLearner/DisenGraphRep/models/infomax.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 37bd33520c0762ac · report
DGI wwwyyun/HDGI/models/dgi.py community (archive-listed) ran MIT (permissive) · d7d2117d73a0c03d · report
DeepGraphInfomax Sam131112/Deep-Graph-Infomax-Implementation/deepgraphinfomax.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 18a11990837977e4 · report
Discriminator Sam131112/Deep-Graph-Infomax-Implementation/deepgraphinfomax.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 8ac4c2aa6c924a58 · report
Discriminator Sean-Bin-Yang/Path-InfoMax/models/pim.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 3e0b949d70c76ab4 · report
EncoderLSTM Sean-Bin-Yang/Path-InfoMax/models/pim.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 9a35f79723ddacf3 · report
GCN wwwyyun/HDGI/models/dgi.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 5fd25f0307b96798 · report
GCN zpeng27/GMI/models/gmi.py community (archive-listed) ran MIT (permissive) · 1efc738df1839678 · report
GraphConvolutionLayer Sam131112/Deep-Graph-Infomax-Implementation/deepgraphinfomax.py community (archive-listed) ran no licence file found · pointer only · 3410df5150572826 · report
Normal SpaceLearner/DisenGraphRep/models/infomax.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 7af5f07d76374e95 · report
Readout Sam131112/Deep-Graph-Infomax-Implementation/deepgraphinfomax.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 5c44b5cacba28aaa · report
Readout Sean-Bin-Yang/Path-InfoMax/models/pim.py community (archive-listed) ran fingerprinted no licence file found · pointer only · ebd1fd43842156d6 · report
STHeaviside SpaceLearner/DisenGraphRep/models/infomax.py community (archive-listed) ran MIT (permissive) · 72705e2c2924fe8c · report
entropy wwwyyun/HDGI/execute.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · f5bc6debaeb77061 · report
idx2onehot ngminhhieu/DGI/utils/dgi/process.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · e0eb450eeb67bbe7 · report
load_data dfdazac/dgi/gcn/utils.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 36d8bb4858e7bb51 · report
logsumexp SpaceLearner/DisenGraphRep/models/infomax.py community (archive-listed) ran · our draft was wrong MIT (permissive) · ef2e8969dc4b82fe · report
prune wwwyyun/HDGI/execute.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · e853d6332902fb5f · report
sample_mask dfdazac/dgi/gcn/utils.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · b32fd748b4bbe3bf · report
AvgNeighbor zpeng27/GMI/models/gmi.py community (archive-listed) unverified MIT (permissive) · 27f7cf29d9108df6 · report
DeepGraphInfomax SpaceLearner/DisenGraphRep/models/infomax.py community (archive-listed) unverified MIT (permissive) · 5aa5707ddd7c40ca · report
Discriminator wwwyyun/HDGI/models/dgi.py community (archive-listed) unverified MIT (permissive) · 690842e491f017bd · report
Discriminator zpeng27/GMI/models/gmi.py community (archive-listed) unverified MIT (permissive) · e31d20ab111c4457 · report
GMI zpeng27/GMI/models/gmi.py community (archive-listed) unverified MIT (permissive) · e1c0b15be5eb9e7f · report
PIM Sean-Bin-Yang/Path-InfoMax/models/pim.py community (archive-listed) unverified no licence file found · pointer only · 17418975d54cd5c9 · report
logsumexp SpaceLearner/DisenGraphRep/models/dgi.py community (archive-listed) unverified MIT (permissive) · 5b63bfbc3d382b97 · report
parse_skipgram ngminhhieu/DGI/utils/dgi/process.py community (archive-listed) unverified MIT (permissive) · 47c9a03fbd1720a3 · report
process_tu ngminhhieu/DGI/utils/dgi/process.py community (archive-listed) unverified MIT (permissive) · 10796842869164d2 · report
reset SpaceLearner/DisenGraphRep/models/infomax.py community (archive-listed) unverified MIT (permissive) · 63491bdac79e3e64 · report
uniform SpaceLearner/DisenGraphRep/models/infomax.py community (archive-listed) unverified MIT (permissive) · aee2e93dc7075ef3 · report
parse_index_file identical code first harvested elsewhere ran · honoured contract licence of this copy not recorded · c1d6392f89c5e495 · report

Tasks

General ClassificationInductive LearningNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Citeseer DGI Accuracy 71.8 ± 0.7% #48 of 71 Archive leaderboard report
Node Classification Cora DGI Accuracy 82.3 ± 0.6% #52 of 73 Archive leaderboard report
Node Classification Pubmed DGI Accuracy 76.8 ± 0.6% #62 of 70 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: DGI

DGI

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