SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.07594 · ICML · 2021

Graph Contrastive Learning Automated

Tianlong Chen, Zhangyang Wang, Yuning You, Yang Shen

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2106.07594.json · badge: /api/ran/2106.07594.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
shen-lab/graphcl_automated canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
Shen-Lab/GraphCL_Automated marked official in Papers with Code
Papers with Code archive
1 ran · 1 no recorded run
chao1224/graphmvp community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Encoder Ran
ran on a synthesized input
Shen-Lab/GraphCL_Automated/unsupervised_TU/joao.py
pointer only (licence: NONE) · get_code("0b0d72d70fed5ac3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Shen-Lab/GraphCL_Automated when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cycle_index Ran
ran, honoured the contract we drafted
shen-lab/graphcl_automated/transferLearning_MoleculeNet_PPI/bio/pretrain_joao.py
pointer only (licence: NONE) · get_code("b822dd00427403bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen-lab/graphcl_automated when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

graphcl Ran
ran on a synthesized input · constructed an object; no result was computed
chao1224/graphmvp/src_classification/pretrain_JOAOv2.py
code served (permissive licence) · get_code("a2d3c0ee16ce7cc9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, graphcl: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch_geometric.nn import global_mean_pool

torch.manual_seed(0)

# Create a small stand-in GNN module that takes (x, edge_index, edge_attr) and returns node embeddings
class SimpleGNN(nn.Module):
    def __init__(self):
        super(SimpleGNN, self).__init__()
        self.linear = nn.Linear(4, 300)
    
    def forward(self, x, edge_index, edge_attr):
        # x: [num_nodes, 4]
        # Returns: [num_nodes, 300]
        return self.linear(x)

# Instantiate the GNN
gnn = SimpleGNN()

ARGS = {
    "gnn": gnn
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type graphcl — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a graphcl output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
GcnInfomax Not yet run
unverified (harvested, no recorded run)
Shen-Lab/GraphCL_Automated/unsupervised_TU/joao.py
pointer only (licence: NONE) · get_code("c0a9a5dc5a28a4a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Shen-Lab/GraphCL_Automated when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
shen-lab/graphcl_automated/semisupervised_OGB/code/main_pretrain_graphcl_joao.py
pointer only (licence: NONE) · get_code("169c3379d3f0bda6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen-lab/graphcl_automated when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
shen-lab/graphcl_automated/transferLearning_MoleculeNet_PPI/bio/pretrain_joao.py
pointer only (licence: NONE) · get_code("4a1d1036ace0997f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shen-lab/graphcl_automated when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
cycle_index 8 other papers
2 dated earlier, 6 later
1905.12265 (2019-05)
Strategies for Pre-training Graph Neural Networks
2010.13902 (2020-10)
Graph Contrastive Learning with Augmentations
2212.10789 (2022-12)
Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing
and 5 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Self-supervised learning on graph-structured data has drawn recent interest for learning generalizable, transferable and robust representations from unlabeled graphs. Among many, graph contrastive learning (GraphCL) has emerged with promising representation learning performance. Unfortunately, unlike its counterpart on image data, the effectiveness of GraphCL hinges on adhoc data augmentations, which have to be manually picked per dataset, by either rules of thumb or trial-and-errors, owing to the diverse nature of graph data. That significantly limits the more general applicability of GraphCL. Aiming to fill in this crucial gap, this paper proposes a unified bilevel optimization framework to automatically, adaptively and dynamically select data augmentations when performing GraphCL on specific graph data. The general framework, dubbed JOint Augmentation Optimization (JOAO), is instantiated as min-max optimization. The selections of augmentations made by JOAO are shown to be in general aligned with previous "best practices" observed from handcrafted tuning: yet now being automated, more flexible and versatile. Moreover, we propose a new augmentationaware projection head mechanism, which will route output features through different projection heads corresponding to different augmentations chosen at each training step. Extensive experiments demonstrate that JOAO performs on par with or sometimes better than the state-ofthe-art competitors including GraphCL, on multiple graph datasets of various scales and types, yet without resorting to any laborious datasetspecific tuning on augmentation selection. We release the code at https://github.com/ Shen-Lab/GraphCL_Automated.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.07594")
get_code_for_paper("2106.07594")
have("2106.07594")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2106.07594.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2106.07594.svg)](https://syntology.ai/paper/2106.07594)

Connect an agent — have() is free.