Papers › Deep Graph Infomax
Deep Graph Infomax
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.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="1809.10341")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1809.10341", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1809.10341")
Code
Syntology 35 code samples: 34 from 8 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 35: 26 ran (of which 11 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 3 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 31 samples from 7 repositories, 22 ran (18 with no instrument failure; 4 where Syntology's instrument failed); 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.
No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:
- egyptdj/graph-neural-mapping, community (archive-listed): harvested for another paper, listed under the repository
- dmlc/dgl, community (archive-listed): harvested for 6 other papers, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 26 samples that ran has no recorded date.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
35 samples harvested: 26 ran (of which 11 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 1 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 10 of the 35 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
7f96e512dd0bcc96 · report
fixture: signature seq:Tensor/3/float, msk:Tensor/2/bool · returned Tensor · level recorded 2026-09-22 58c5f9e1c1f1d371 · report
fixture: signature seq1:Tensor/3/float, seq2:Tensor/3/float, adj:Tensor/3/float, sparse:bool/0/bool, msk:Tensor/2/float, samp_bias1:NoneType/0/?, samp_bias2:NoneType/0/? · returned Tensor · level recorded 2026-09-24 1702410d0868c8a5 · report
fixture: returned Discriminator · level recorded 2026-09-22 18a11990837977e4 · report
fixture: returned DeepGraphInfomax · level recorded 2026-09-22 8ac4c2aa6c924a58 · report
fixture: returned Discriminator · level recorded 2026-09-22 3410df5150572826 · report
fixture: signature input:Tensor/2/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-24 5c44b5cacba28aaa · report
fixture: signature feats:Tensor/2/float · returned Tensor · level recorded 2026-09-24 3e0b949d70c76ab4 · report
fixture: returned Discriminator · level recorded 2026-09-22 9a35f79723ddacf3 · report
fixture: returned EncoderLSTM · level recorded 2026-09-22 ebd1fd43842156d6 · report
fixture: signature seq:Tensor/3/float, msk:Tensor/3/float · returned Tensor · level recorded 2026-09-24 37bd33520c0762ac · report
fixture: returned Bernoulli · level recorded 2026-09-22 7af5f07d76374e95 · report
fixture: returned Normal · level recorded 2026-09-22 72705e2c2924fe8c · report
fixture: returned STHeaviside · level recorded 2026-09-22 census: 8 implementations from 12 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 models/infomax.py ran · our draft was wrong MIT (permissive) ·
ef2e8969dc4b82fe · report
fixture: signature value:Tensor/2/float, dim:int/0/int, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-22 census: 8 implementations from 12 papers, 4 distinct outputs across 2 buckets, one shared input per bucket models/dgi.py unverified MIT (permissive) ·
5b63bfbc3d382b97 · report
36d8bb4858e7bb51 · report
fixture: signature dataset_str:str/0/str · returned tuple · level recorded 2026-09-22 census: 4 implementations from 5 papers, 4 distinct outputs on one shared input gcn/utils.py ran · violated contract fingerprinted MIT (permissive) ·
b32fd748b4bbe3bf · report
fixture: signature idx:int/0/int, l:int/0/int · returned ndarray · level recorded 2026-09-22 e0eb450eeb67bbe7 · report
fixture: signature idx:Tensor/1/int, n:int/0/int · returned Tensor · level recorded 2026-09-22 47c9a03fbd1720a3 · report
fixture: signature fname:str/0/str · returned ndarray · level recorded 2026-09-24 10796842869164d2 · report
fixture: signature data:MockDataset/0/?, nb_nodes:int/0/int · returned tuple · level recorded 2026-09-24 0e9cd1335cbb2931 · report
fixture: returned Assign · level recorded 2026-09-22 d7d2117d73a0c03d · report
fixture: returned DGI · level recorded 2026-09-22 5fd25f0307b96798 · report
fixture: returned GCN · level recorded 2026-09-22 census: 22 implementations from 25 papers, 16 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 2 of 4, arg 1: rank 1, kind float, dtype float32 execute.py ran · honoured contract fingerprinted MIT (permissive) ·
f5bc6debaeb77061 · report
fixture: signature x:Tensor/1/float · returned Tensor · level recorded 2026-09-22 e853d6332902fb5f · report
fixture: signature edge_index:Tensor/2/int, y:Tensor/2/float · returned Tensor · level recorded 2026-09-22 1efc738df1839678 · report
fixture: signature seq:Tensor/3/float, adj:Tensor/2/float · returned tuple · level recorded 2026-09-24 1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
c1d6392f89c5e495 · report
fixture: signature filename:str/0/str · returned list · level recorded, date not recorded Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.
6 assemblies on this paper: 6 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
6 sibling assemblies for Deep Graph Infomax (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Deep Graph Infomax (graph method: Deep Graph Infomax). 7 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- DeepGraphInfomax entry · level 0 · unverified ·
5aa5707ddd7c40ca - Bernoulli helper · level 1 · ran ·
37bd33520c0762ac - Normal helper · level 1 · ran ·
7af5f07d76374e95 - logsumexp helper · level 1 · ran · our draft was wrong ·
ef2e8969dc4b82fe - reset helper · level 0 · unverified ·
63491bdac79e3e64 - uniform helper · level 0 · unverified ·
aee2e93dc7075ef3 - STHeaviside helper · level 1 · ran ·
72705e2c2924fe8c
harvested Assembly for Deep Graph Infomax (graph method: Deep Graph Infomax). 4 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 6 siblings
- DGI entry · level 1 · ran ·
d7d2117d73a0c03d - Assign helper · level 1 · ran ·
0e9cd1335cbb2931 - Discriminator loss · level 0 · unverified ·
690842e491f017bd - GCN model · level 1 · ran ·
5fd25f0307b96798
harvested Assembly for Deep Graph Infomax (graph method: Deep Graph Infomax). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- DeepGraphInfomax entry · level 1 · ran ·
18a11990837977e4 - Discriminator loss · level 1 · ran ·
8ac4c2aa6c924a58 - GraphConvolutionLayer model · level 1 · ran ·
3410df5150572826 - Readout helper · level 1 · ran ·
5c44b5cacba28aaa
harvested Assembly for Deep Graph Infomax (graph method: Deep Graph Infomax). 4 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- PIM entry · level 0 · unverified ·
17418975d54cd5c9 - Discriminator model · level 1 · ran ·
3e0b949d70c76ab4 - EncoderLSTM model · level 1 · ran ·
9a35f79723ddacf3 - Readout helper · level 1 · ran ·
ebd1fd43842156d6
harvested Assembly for Deep Graph Infomax (graph method: Deep Graph Infomax). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- DGI entry · level 1 · ran ·
58c5f9e1c1f1d371 - AvgReadout model · level 1 · ran ·
7f96e512dd0bcc96 - Discriminator model · level 1 · ran ·
1702410d0868c8a5 - GCN model · level 1 · ran ·
5fd25f0307b96798
harvested Assembly for Deep Graph Infomax (graph method: Deep Graph Infomax). 4 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 6 siblings
- GMI entry · level 0 · unverified ·
e1c0b15be5eb9e7f - AvgNeighbor helper · level 0 · unverified ·
27f7cf29d9108df6 - Discriminator model · level 0 · unverified ·
e31d20ab111c4457 - GCN model · level 1 · ran ·
1efc738df1839678
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1809.10341") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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