Papers › Graph Contrastive Learning with Augmentations

Graph Contrastive Learning with Augmentations

22 Oct 2020NeurIPS 2020 12arXiv:2010.13902archive 2025-07-28

Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang shen

Generalizable, transferrable, and robust representation learning on graph-structured data remains a challenge for current graph neural networks (GNNs). Unlike what has been developed for convolutional neural networks (CNNs) for image data, self-supervised learning and pre-training are less explored for GNNs. In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data. We first design four types of graph augmentations to incorporate various priors. We then systematically study the impact of various combinations of graph augmentations on multiple datasets, in four different settings: semi-supervised, unsupervised, and transfer learning as well as adversarial attacks. The results show that, even without tuning augmentation extents nor using sophisticated GNN architectures, our GraphCL framework can produce graph representations of similar or better generalizability, transferrability, and robustness compared to state-of-the-art methods. We also investigate the impact of parameterized graph augmentation extents and patterns, and observe further performance gains in preliminary experiments. Our codes are available at https://github.com/Shen-Lab/GraphCL.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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):

Code

Syntology 19 code samples harvested from 4 repositories linked to this paper: 17 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 14 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 18 samples from 3 repositories, 16 ran (2 with no instrument failure; 14 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 17 samples that ran have no recorded date.

Shen-Lab/GraphCL officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Shen-Lab/GraphCL_Automated mentioned on GitHubpytorchSyntology: 7 samples, 6 ran (5 instrument-failed) · 1 unverified report
ycremar/DIG-SSL mentioned on GitHubpytorchSyntology: 10 samples, 9 ran (8 instrument-failed) · 1 unverified report
yuwvandy/g2gnn mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified 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

19 samples harvested: 17 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 14 where Syntology's instrument failed) · 2 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.

1ran · honoured contract
10ran · our draft was wrong
4ran; the contract check could not run
2ran
2unverified

Licence: 18 of the 19 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 4 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 whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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.

Shen-Lab/GraphCL official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
graphcl transferLearning_MoleculeNet_PPI/chem/pretrain_graphcl.py ran · metamorphic tier: deterministic MIT (permissive) · 80ece471102b74f3 · report fixture: returned graphcl · level recorded 2026-09-22
Shen-Lab/GraphCL_Automated community (archive-listed) 7 samples, 6 ran (5 instrument-failed) · 1 unverified
cycle_index in 9 papers transferLearning_MoleculeNet_PPI/bio/pretrain_joao.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract licence of this copy not recorded · b822dd00427403bf · report fixture: signature num:int/0/int, shift:int/0/int · returned Tensor · level recorded, date not recorded
drop_nodes in 6 papers unsupervised_TU/aug.py ran · our draft was wrong no licence file found · pointer only · 9d6cd266e78dc80f · report fixture: signature data:MockData/0/? · returned MockData · level recorded 2026-09-22
mask_nodes in 5 papers unsupervised_TU/aug.py ran · our draft was wrong no licence file found · pointer only · 122a8f8967440f5a · report fixture: signature data:MockData/0/? · returned MockData · level recorded 2026-09-22
permute_edges in 5 papers unsupervised_TU/aug.py ran · our draft was wrong no licence file found · pointer only · 4e5d7db5f75c30b6 · report fixture: signature data:MockData/0/? · returned MockData · level recorded 2026-09-22
subgraph in 6 papers unsupervised_TU/aug.py ran · our draft was wrong no licence file found · pointer only · f679d89508183977 · report fixture: signature data:MockData/0/? · returned MockData · level recorded 2026-09-22
train in 522 papers transferLearning_MoleculeNet_PPI_LP/bio/pretrain_generative_infobn.py ran · our draft was wrong no licence file found · pointer only · 84567ef3dc4cb159 · report fixture: signature args:NoneType/0/?, loader:list/1/tuple, model_cl:callable/0/?, optimizer_cl:Adam/0/?, model_1:callable/0/?, optimizer_1:Adam/0/?, model_2:callable/0/?, optimizer_2:Adam/0/?, model_ib:callable/0/?, optimizer_ib:Adam/0/?, device:device/0/? · returned tuple · level recorded, date not recorded
TUDataset_aug unsupervised_TU/aug.py unverified no licence file found · pointer only · a74955e8b458fc65 · report
ycremar/DIG-SSL community (archive-listed) 10 samples, 9 ran (8 instrument-failed) · 1 unverified
Contrastive sslgraph/contrastive/model/graphcl.py ran · metamorphic tier: deterministic no licence file found · pointer only · 7359e4334ef6272b · report fixture: returned Contrastive · level recorded 2026-09-22
NCE_loss sslgraph/contrastive/model/graphcl.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 9f253c62c8e84cf5 · report fixture: signature zs:list/1/Tensor, zs_n:NoneType/0/?, batch:NoneType/0/?, sigma:NoneType/0/?, tau:float/0/float, norm:bool/0/bool · returned Tensor · level recorded 2026-09-22
NT_Xent in 8 papers sslgraph/contrastive/model/graphcl.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · b5812fc5a667e0d5 · report fixture: signature z1:Tensor/2/float, z2:Tensor/2/float, tau:float/0/float, norm:bool/0/bool · returned Tensor · level recorded 2026-09-22
RW_sample sslgraph/contrastive/model/graphcl.py ran · our draft was wrong no licence file found · pointer only · a28760ba97472616 · report fixture: signature ratio:float/0/float, add_self_loop:bool/0/bool · returned function · level recorded 2026-09-22
edge_perturbation sslgraph/contrastive/model/graphcl.py ran · our draft was wrong no licence file found · pointer only · 40eabff12d968735 · report fixture: signature add:bool/0/bool, drop:bool/0/bool, ratio:float/0/float · returned function · level recorded 2026-09-22
infoNCE_local_intra_node sslgraph/contrastive/model/graphcl.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 1045b0a0a750926e · report fixture: signature z1_n:Tensor/2/float, z2_n:Tensor/2/float, tau:float/0/float, norm:bool/0/bool · returned Tensor · level recorded 2026-09-22
node_attr_mask sslgraph/contrastive/model/graphcl.py ran · our draft was wrong no licence file found · pointer only · 565cd376d19d16fe · report fixture: signature mode:str/0/str, mask_ratio:float/0/float, mask_mean:float/0/float, mask_std:float/0/float · returned function · level recorded 2026-09-22
random_view sslgraph/contrastive/model/graphcl.py ran · our draft was wrong no licence file found · pointer only · 6a784308a8c084d2 · report fixture: signature candidates:list/1/callable · returned function · level recorded 2026-09-22
uniform_sample in 7 papers sslgraph/contrastive/model/graphcl.py ran · our draft was wrong no licence file found · pointer only · 5d7733a471ca27b8 · report fixture: signature ratio:float/0/float · returned function · level recorded 2026-09-22
GraphCL sslgraph/contrastive/model/graphcl.py unverified no licence file found · pointer only · 8130b63d6ab585fa · report
yuwvandy/g2gnn community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
remove_edge aug.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 2ac6b4ffab6287ac · report fixture: signature edge_index:Tensor/2/int, drop_ratio:float/0/float · returned Tensor · level recorded 2026-09-22

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.

4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

4 sibling assemblies for GraphCL (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for GraphCL (graph method: GraphCL). 1 brick; individually on a fixture: 1 ran (of which 1 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) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. graphcl entry · level 1 · ran · 80ece471102b74f3

harvested Assembly for GraphCL (graph method: GraphCL). 11 bricks; individually on a fixture: 9 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. GraphCL entry · level 0 · unverified · 8130b63d6ab585fa
  2. Contrastive model · level 1 · ran · 7359e4334ef6272b
  3. RW_sample helper · level 1 · ran · our draft was wrong · a28760ba97472616
  4. edge_perturbation data_transform · level 1 · ran · our draft was wrong · 40eabff12d968735
  5. node_attr_mask helper · level 1 · ran · our draft was wrong · 565cd376d19d16fe
  6. random_view helper · level 1 · ran · our draft was wrong · 6a784308a8c084d2
  7. uniform_sample helper · level 1 · ran · our draft was wrong · 5d7733a471ca27b8
  8. NCE_loss loss · level 1 · ran; the contract check could not run (RAISES) · 9f253c62c8e84cf5
  9. NT_Xent loss · level 1 · ran; the contract check could not run (RAISES) · b5812fc5a667e0d5
  10. infoNCE_local_global loss · level 0 · unverified · ff71bf49cbcabcf0
  11. infoNCE_local_intra_node loss · level 1 · ran; the contract check could not run (RAISES) · 1045b0a0a750926e

harvested Assembly for GraphCL (graph method: GraphCL). 5 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. TUDataset_aug entry · level 0 · unverified · a74955e8b458fc65
  2. drop_nodes data_transform · level 1 · ran · our draft was wrong · 9d6cd266e78dc80f
  3. mask_nodes data_transform · level 1 · ran · our draft was wrong · 122a8f8967440f5a
  4. permute_edges data_transform · level 1 · ran · our draft was wrong · 4e5d7db5f75c30b6
  5. subgraph data_transform · level 1 · ran · our draft was wrong · f679d89508183977

harvested Assembly for GraphCL (graph method: GraphCL). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. remove_edge entry · level 1 · ran; the contract check could not run (RAISES) · 2ac6b4ffab6287ac

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="2010.13902") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningRepresentation LearningSelf-Supervised LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: GraphCL

Contrastive LearningGraphCL

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