SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.09963 · 2020

GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 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/2006.09963.json · badge: /api/ran/2006.09963.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
THUDM/GCC canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
create_node_classification_dataset Ran
ran on a synthesized input
THUDM/GCC/gcc/datasets/data_util.py
code served (permissive licence) · get_code("8f2a75222457cf8e")
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 Edgelist. 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 os
import tempfile
from collections import defaultdict
import torch

torch.manual_seed(0)

# Create temporary directories and files for testing
tmpdir = tempfile.mkdtemp()

# Create struc2vec directory structure for airport dataset
struc2vec_dir = os.path.join(tmpdir, 'data', 'struc2vec')
os.makedirs(struc2vec_dir, exist_ok=True)

# Create usa-airports.edgelist and usa-airports.nodelabel
with open(os.path.join(struc2vec_dir, 'usa-airports.edgelist'), 'w') as f:
    f.write("1 2\n")
    f.write("2 3\n")

with open(os.path.join(struc2vec_dir, 'usa-airports.nodelabel'), 'w') as f:
    f.write("1 0\n")
    f.write("2 1\n")
    f.write("3 0\n")

# Create hindex directory structure
hindex_dir = os.path.join(tmpdir, 'data', 'hindex')
os.makedirs(hindex_dir, exist_ok=True)

with open(os.path.join(hindex_dir, 'aminer_hindex_rand1_5000.edgelist'), 'w') as f:
    f.write("1 2\n")
    f.write("2 3\n")

with open(os.path.join(hindex_dir, 'aminer_hindex_rand1_5000.nodelabel'), 'w') as f:
    f.write("1 100\n")
    f.write("2 200\n")
    f.write("3 150\n")

# Create panther directory structure
panther_dir = os.path.join(tmpdir, 'data', 'panther')
os.makedirs(panther_dir, exist_ok=True)

with open(os.path.join(panther_dir, 'kdd.graph'), 'w') as f:
    f.write("3 2\n")  # header line
    f.write("1 2 1\n")
    f.write("2 3 1\n")

# Patch os.path to use our tmpdir
original_join = os.path.join
def patched_join(*args):
    if len(args) > 0 and args[0].startswith('data/'):
        return original_join(tmpdir, *args)
    return original_join(*args)

os.path.join = patched_join

ARGS = {
    'dataset_name': 'usa_airport'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Edgelist — a Edgelist output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Edgelist 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
eigen_decomposision Ran
ran on a synthesized input
THUDM/GCC/gcc/datasets/data_util.py
code served (permissive licence) · get_code("1fb4d926d726bafc")
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 Tensor, ndim 2, dtype family float, shape (8, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np
import scipy.sparse as sparse
import sklearn.preprocessing as preprocessing
import torch
import torch.nn.functional as F
from scipy.sparse import linalg

torch.manual_seed(0)

# Create a small sparse matrix to act as a Laplacian
# A Laplacian is typically symmetric and positive semi-definite
n = 8
# Create a simple sparse symmetric matrix (graph Laplacian)
row = np.array([0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7])
col = np.array([0, 1, 2, 1, 2, 3, 4, 3, 4, 5, 6, 5, 6, 7, 0])
data = np.array([2.0, 2.0, -1.0, 2.0, -1.0, 2.0, -1.0, 2.0, -1.0, 2.0, -1.0, 2.0, -1.0, 2.0, -1.0])
laplacian = sparse.csr_matrix((data, (row, col)), shape=(n, n), dtype='float64')
laplacian = laplacian + laplacian.T  # Make it symmetric

k = 3
hidden_size = 6
retry = 2

ARGS = {
    'n': n,
    'k': k,
    'laplacian': laplacian,
    'hidden_size': hidden_size,
    'retry': retry,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (8, 6) — shape (8, 6) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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.

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

Graph representation learning has emerged as a powerful technique for addressing real-world problems. Various downstream graph learning tasks have benefited from its recent developments, such as node classification, similarity search, and graph classification. However, prior arts on graph representation learning focus on domain specific problems and train a dedicated model for each graph dataset, which is usually non-transferable to out-of-domain data. Inspired by the recent advances in pre-training from natural language processing and computer vision, we design Graph Contrastive Coding (GCC) -- a self-supervised graph neural network pre-training framework -- to capture the universal network topological properties across multiple networks. We design GCC's pre-training task as subgraph instance discrimination in and across networks and leverage contrastive learning to empower graph neural networks to learn the intrinsic and transferable structural representations. We conduct extensive experiments on three graph learning tasks and ten graph datasets. The results show that GCC pre-trained on a collection of diverse datasets can achieve competitive or better performance to its task-specific and trained-from-scratch counterparts. This suggests that the pre-training and fine-tuning paradigm presents great potential for graph representation learning.

For agents

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

get_harvested_code_for_paper("2006.09963")
get_code_for_paper("2006.09963")
have("2006.09963")

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

curl https://syntology.ai/api/ran/2006.09963.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.09963.svg)](https://syntology.ai/paper/2006.09963)

Connect an agent — have() is free.