Papers › Semi-Supervised Classification with Graph Convolutional Networks

Semi-Supervised Classification with Graph Convolutional Networks

9 Sep 2016arXiv:1609.02907archive 2025-07-28

Thomas N. Kipf, Max Welling

We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes. In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.

PaperPDFCodeCode 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

No sample from the archive's official repository (tkipf/pygcn) is linked to this paper; the 58 samples below come from 29 community repositories. Syntology harvested code from tkipf/pygcn for another paper.

tkipf/pygcn: Syntology's graph links these samples to Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration (arXiv:2109.14285; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 58 code samples harvested from 29 repositories linked to this paper: 39 ran (of which 13 constructed an object rather than computing a result; 34 with no instrument failure: 0 honoured, 1 violated, 33 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 58 samples from 29 repositories, 39 ran (34 with no instrument failure; 5 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.

No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

55 repositories listed; official and paper-mentioned ones first.

tkipf/pygcn officialmentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration (arXiv:2109.14285; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
tkipf/gcn mentioned in papermentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs (arXiv:2006.11468; that paper's own run record: 16 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 2 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
1075225782/GCN mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
30Aniket/Graph-Convolutional-Networks-GCNs mentioned on GitHubSyntology: not harvested report
HoganZhang/pygcn_python3 mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
IllinoisGraphBenchmark/IGB-Datasets mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
KimMeen/GCN mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
LouisDumont/GCN---re-implementation mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
abi-kothapalli/minimumdominatingsets mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
ajbisberg/gcn mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (arXiv:1606.09375; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
alexOarga/haiku-geometric mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Principal Neighbourhood Aggregation for Graph Nets (arXiv:2004.05718; that paper's own run record: 33 ran (of which 4 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 22 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
asif-salim/GCN-Graph_Convolutional_Network mentioned on GitHubtfSyntology: not harvested report
basiralab/RG-Select mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
basiralab/Reproducible-Generative-Learning mentioned on GitHubpytorchSyntology: not harvested report
basiralab/reproduciblefedgnn mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hierarchical Graph Representation Learning with Differentiable Pooling (arXiv:1806.08804; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
bcsrn/gcn mentioned on GitHubpytorchSyntology: not harvested report
bepping/non-oversmoothing-gcns mentioned on GitHubSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
clin366/pygcn mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
cybermonic/cage-4-submission mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (2 instrument-failed) · 0 unverified report
darnbi/pygcn mentioned on GitHubpytorchMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
deepchem/moleculenet mentioned on GitHubpytorchSyntology: not harvested report
emartinezs44/SparkGCN mentioned on GitHubSyntology: not harvested report
fanzhenliu/dagad mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
hazdzz/GCN mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
jiangboahu/glcn-tf mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
kiharalab/gnn_pocket mentioned on GitHubtorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lipingcoding/pygcn mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
mahendrathapa/graph-convolution-network mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
mahsa91/GKD mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
mahsa91/RA-GCN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
meliketoy/graph-cnn.pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting Semi-Supervised Learning with Graph Embeddings (arXiv:1603.08861; that paper's own run record: 15 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 2 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified) and Graph Attention Networks (arXiv:1710.10903; that paper's own run record: 61 ran (of which 28 constructed an object rather than computing a result; 52 with no instrument failure: 1 honoured, 2 violated, 49 with no contract checked; 9 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
negarhdr/PGCN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
nieci2024/pyglcn mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (1 instrument-failed) · 2 unverified report
nnaakkaaii/g2-MLP mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
selmiss/gp-tlstgcn mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
thanhtrunghuynh93/pygcn mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tk-rusch/graphcon mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Graph-Coupled Oscillator Networks (arXiv:2202.02296; that paper's own run record: 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) · 0 unverified) and Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach (arXiv:2310.06396; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
tkipf/keras-gcn mentioned on GitHubtfMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
toinesayan/node-classification-and-label-dependencies mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
tuananh0305/GCN_ANOMALY_DETECTION mentioned on GitHubSyntology: not harvested report
udlf/wsef mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
yCobanoglu/infinite-width-gnns mentioned on GitHubjaxSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
yangjun1994/CAGCN mentioned on GitHubSyntology: not harvested report
yanhuchen/quantum-graph-convolutional-network mentioned on GitHubMITSyntology: not harvested report
ykrmm/sota_gnn mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
zhiqiang00/Hon-GCN mentioned on GitHubpytorchMITSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report
2023-MindSpore-1/ms-code-11 mindsporeSyntology: not harvested report
HamzaGbada/GCN-Numpy pytorchSyntology: 4 samples, 0 ran · 4 unverified report
alililia/ms_contrib mindsporeSyntology: not harvested report
alililia/ms_contrib mindsporeSyntology: not harvested report
dmlc/dgl pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to node2vec: Scalable Feature Learning for Networks (arXiv:1607.00653; that paper's own run record: 15 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified), Interaction Networks for Learning about Objects, Relations and Physics (arXiv:1612.00222; that paper's own run record: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result), Junction Tree Variational Autoencoder for Molecular Graph Generation (arXiv:1802.04364; that paper's own run record: 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) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
dmlc/dgl pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to node2vec: Scalable Feature Learning for Networks (arXiv:1607.00653; that paper's own run record: 15 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified), Interaction Networks for Learning about Objects, Relations and Physics (arXiv:1612.00222; that paper's own run record: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result), Junction Tree Variational Autoencoder for Molecular Graph Generation (arXiv:1802.04364; that paper's own run record: 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) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
mahequn001/graphlearning mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to How Attentive are Graph Attention Networks? (arXiv:2105.14491; that paper's own run record: 11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
sunxiaobei/mindspore_gallery mindsporeSyntology: not harvested 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.

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

58 samples harvested: 39 ran (of which 13 constructed an object rather than computing a result; 34 with no instrument failure: 0 honoured, 1 violated, 33 with no contract checked; 5 where Syntology's instrument failed) · 19 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 · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
33ran
19unverified

Licence: 23 of the 58 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 29 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. “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.

1075225782/GCN community (archive-listed) 1 sample, 0 ran · 1 unverified
GCN in 41 papers GCN/gcnpy/models.py unverified no licence file found · pointer only · 9ae4971fbc72a790 · report
HoganZhang/pygcn_python3 community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
GCN in 41 papers pygcn/models.py ran · metamorphic tier: invariant MIT (permissive) · c6a324398743dc52 · report fixture: signature x:Tensor/2/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GraphConvolution in 36 papers pygcn/models.py ran · metamorphic tier: invariant MIT (permissive) · 87d10d793f9fe9bc · report fixture: signature input:Tensor/2/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-22
KimMeen/GCN community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
evaluate in 514 papers train_citeseer.py ran Apache-2.0 (permissive) · e16659d9314db70e · report fixture: signature model:callable/0/?, graph:SimpleGraph/0/?, features:Tensor/2/float, labels:Tensor/1/int, mask:Tensor/1/bool · returned float · level recorded 2026-09-26
LouisDumont/GCN---re-implementation community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GCN in 41 papers gcn.py ran · metamorphic tier: deterministic no licence file found · pointer only · c58cace7f8be77e2 · report fixture: returned GCN · level recorded 2026-09-22
abi-kothapalli/minimumdominatingsets community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
Layer in 20 papers gcn/layers.py ran fingerprinted MIT (permissive) · 69193fc7101cf090 · report fixture: signature inputs:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24
GraphConvolution in 36 papers gcn/layers.py unverified MIT (permissive) · 0613cab4515d9b95 · report
basiralab/RG-Select community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
GraphConvolution in 36 papers models_gcn.py ran · metamorphic tier: invariant no licence file found · pointer only · 2c8ae246b26bbe8a · report fixture: signature input:Tensor/2/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GCN in 41 papers models_gcn.py unverified no licence file found · pointer only · 0a27b9c97ef96c4c · report
bepping/non-oversmoothing-gcns community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
GCNGP src/GCN_methods/models.py ran MIT (permissive) · 7ce73b453b28e799 · report fixture: returned GCNGP · level recorded 2026-09-22
Linearized_GP src/GCN_methods/models.py ran MIT (permissive) · 086f2aa4471b98ee · report fixture: returned Linearized_GP · level recorded 2026-09-22
GCN in 41 papers src/GCN_methods/models.py unverified MIT (permissive) · 33c9884171e760fd · report
clin366/pygcn community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
encode_onehot in 24 papers
census: 3 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
pygcn/utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 3ab88254add4c192 · report fixture: signature labels:ndarray/1/int · returned ndarray · level recorded 2026-09-22
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
pygcn/utils.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · aa9c29936dee40a7 · report fixture: signature mx:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-22
load_data in 700 papers pygcn/utils.py unverified MIT (permissive) · bf19a66cd72d43f2 · report
cybermonic/cage-4-submission community (archive-listed) 4 samples, 4 ran (2 instrument-failed) · 0 unverified
InductiveCriticNetwork models/cage4.py ran GPL-2.0 (copyleft) · pointer only · 85bd4acab3d8c054 · report fixture: signature x:Tensor/2/float, ei:Tensor/2/int, global_vec:Tensor/2/float, servers:Tensor/1/int, n_servers:Tensor/1/int, users:Tensor/1/int, n_users:Tensor/1/int, action_edges:Tensor/2/int, multi_subnet:bool/0/bool · returned Tensor · level recorded 2026-09-24
SimpleSelfAttention models/cage4.py ran GPL-2.0 (copyleft) · pointer only · 054b6e15933ec96b · report fixture: returned SimpleSelfAttention · level recorded 2026-09-22
extract_hosts models/cage4.py ran; the contract check could not run (RAISES) GPL-2.0 (copyleft) · pointer only · 70ca1b92d45e9b26 · report fixture: signature x:Tensor/2/float, servers:Tensor/1/int, n_servers:Tensor/1/int, users:Tensor/1/int, n_users:Tensor/1/int · returned tuple · level recorded 2026-09-22
pad_sequence in 46 papers models/cage4.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · 8df101e74bcddcca · report fixture: signature seq:Tensor/2/float, lens:Tensor/1/int, padding:int/0/int · returned tuple · level recorded 2026-09-22
darnbi/pygcn community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
alignment pygcn/alignment.py ran fingerprinted MIT (permissive) · b56b9aade0ebad51 · report fixture: signature embed_1:ndarray/2/float, embed_2:ndarray/2/float · returned ndarray · level recorded 2026-09-26
encode_onehot in 24 papers
census: 3 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
pygcn/utils.py ran MIT (permissive) · 880de3ec87607e47 · report fixture: signature labels:ndarray/1/int · returned ndarray · level recorded 2026-09-26
naive_alignment pygcn/alignment.py ran fingerprinted MIT (permissive) · da98b40a03dbd482 · report fixture: signature embed_1:ndarray/2/float, embed_2:ndarray/2/float · returned ndarray · level recorded 2026-09-26
load_data in 700 papers pygcn/utils.py unverified MIT (permissive) · 65a9d7324cc70e83 · report
fanzhenliu/dagad community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DAGAD_GCN DAGAD.py ran · metamorphic tier: deterministic MIT (permissive) · d6b36ad879720430 · report fixture: returned DAGAD_GCN · level recorded 2026-09-22
hazdzz/GCN community (archive-listed) 1 sample, 0 ran · 1 unverified
GCN in 41 papers model/models.py unverified LGPL-2.1 (copyleft) · pointer only · c8a2116bdd54211d · report
jiangboahu/glcn-tf community (archive-listed) 1 sample, 0 ran · 1 unverified
GraphConvolution in 36 papers glcn/layers.py unverified no licence file found · pointer only · 143da86eef0cba06 · report
kiharalab/gnn_pocket community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphConvolution in 36 papers model/layers.py ran GPL-3.0 (copyleft) · pointer only · 6a8bc2a8609d02b6 · report fixture: signature input:Tensor/3/float, adj:Tensor/3/float · returned Tensor · level recorded 2026-09-24
lipingcoding/pygcn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
load_data in 700 papers pygcn/utils.py ran MIT (permissive) · 0503d0e1f92b51c3 · report fixture: signature path:str/0/str, dataset:str/0/str · returned tuple · level recorded 2026-09-24
mahendrathapa/graph-convolution-network community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
GCN in 41 papers src/model/gcn.py ran no licence file found · pointer only · 7ad60a09b8387891 · report fixture: returned GCN · level recorded 2026-09-22
GraphConvolution in 36 papers src/model/gcn.py ran no licence file found · pointer only · da1862d885b56f90 · report fixture: signature input:Tensor/2/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-24
mahsa91/RA-GCN community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphConvolution in 36 papers code/layer.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 834a39735e8891ef · report fixture: returned GraphConvolution · level recorded 2026-09-22
negarhdr/PGCN community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphConvolution in 36 papers pgcn/layers.py ran · metamorphic tier: deterministic MIT (permissive) · 2babbec8f9e467b8 · report fixture: returned GraphConvolution · level recorded 2026-09-22
nieci2024/pyglcn community (archive-listed) 4 samples, 2 ran (1 instrument-failed) · 2 unverified
GraphConvolution in 36 papers glcn/layers.py ran · metamorphic tier: deterministic MIT (permissive) · d42e565640a66336 · report fixture: returned GraphConvolution · level recorded 2026-09-22
sparse_dropout in 30 papers glcn/layers.py ran · our draft was wrong fingerprinted MIT (permissive) · 3df97104adae129f · report fixture: signature x:Tensor/2/float, p:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22
glorot_init in 9 papers glcn/layers.py unverified MIT (permissive) · ea40475de51187a2 · report
zeros_init glcn/layers.py unverified MIT (permissive) · ce80770a1e139cfc · report
nnaakkaaii/g2-MLP community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
GCNNode gnn/src/models/networks/gcn_node.py ran · metamorphic tier: deterministic MIT (permissive) · f57b15b48db1c0bc · report fixture: returned GCNNode · level recorded 2026-09-22
Residual in 24 papers gnn/src/models/networks/gcn_node.py ran · metamorphic tier: deterministic MIT (permissive) · 1f6d95f2dbf139ad · report fixture: returned Residual · level recorded 2026-09-22
selmiss/gp-tlstgcn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphConv in 6 papers model/layers.py ran LGPL-2.1 (copyleft) · pointer only · b60e4872344aa92f · report fixture: returned GraphConv · level recorded 2026-09-22
thanhtrunghuynh93/pygcn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
load_data in 700 papers pygcn/utils.py ran MIT (permissive) · 830bf7e364f5b571 · report fixture: signature path:str/0/str, dataset:str/0/str · returned tuple · level recorded 2026-09-26
tkipf/keras-gcn community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
normalize_adj in 55 papers kegra/utils.py ran MIT (permissive) · 835dff62cae2e799 · report fixture: signature adj:csr_matrix/2/float, symmetric:bool/0/bool · returned csr_matrix · level recorded 2026-09-26
load_data in 700 papers kegra/utils.py unverified MIT (permissive) · a1c464c0fd79d7cb · report
toinesayan/node-classification-and-label-dependencies community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
ConvolutionLayer models/gcn.py ran · metamorphic tier: invariant no licence file found · pointer only · 64dec3c1f0c3dc42 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GCN in 41 papers models/gcn.py ran · metamorphic tier: invariant no licence file found · pointer only · 68f1d06e5c89108e · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
udlf/wsef community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Net in 54 papers gcn.py ran GPL-2.0 (copyleft) · pointer only · 8ff00a5cb292d5b8 · report fixture: returned Net · level recorded 2026-09-22
yCobanoglu/infinite-width-gnns community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
GCN in 41 papers gnn/models/node_classification/gcn.py ran · metamorphic tier: invariant no licence file found · pointer only · b28cd994482b4d0a · report fixture: signature adj:Tensor/2/float, x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GraphConv in 6 papers gnn/models/node_classification/gcn.py ran no licence file found · pointer only · 660520aacc4ae7f5 · report fixture: signature x:Tensor/2/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-24
select_nonlinearity gnn/models/node_classification/gcn.py ran · our draft was wrong no licence file found · pointer only · 478cb05c26a9d740 · report fixture: signature nonlinearity:str/0/str · returned function · level recorded 2026-09-22
ykrmm/sota_gnn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Two_Layer_GCN GCN/gcn.py ran no licence file found · pointer only · 81656e9a45a5892b · report fixture: signature A_hat:ndarray/2/float, X:ndarray/2/float · returned Tensor · level recorded 2026-09-24
zhiqiang00/Hon-GCN community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
get_mapping in 5 papers pygcn/utils.py ran MIT (permissive) · c261fb3b4b4f0f06 · report fixture: signature Path:str/0/str · returned dict · level recorded 2026-09-26
get_Graph pygcn/data_processed.py unverified MIT (permissive) · 7db7621c20669aaf · report
get_Graph pygcn/utils.py unverified MIT (permissive) · 3e60fd78554aece2 · report
get_Graph2 pygcn/data_processed.py unverified MIT (permissive) · 41f2caabfb1e3cb4 · report
get_degrees pygcn/data_processed.py unverified MIT (permissive) · e9baa5a7abb70e2e · report
HamzaGbada/GCN-Numpy community (archive-listed) 4 samples, 0 ran · 4 unverified
GCN in 41 papers core/GCN_scratch/model.py unverified MIT (permissive) · 720119c339f1a7f9 · report
GCNLayer in 10 papers core/GCN_scratch/model.py unverified MIT (permissive) · f35bf2b12ecf1db2 · report
GraphUtils core/GCN_scratch/model.py unverified MIT (permissive) · 0946cf496cae35a2 · report
MPNNLayer core/GCN_scratch/model.py unverified MIT (permissive) · ca2f06ead4240f62 · report

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.

23 assemblies on this paper: 23 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

23 sibling assemblies for Graph Convolutional Networks (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 23 sibling assemblies; the other 11 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 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 23 siblings

  1. GraphConvolution entry · level 1 · ran · 834a39735e8891ef

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 23 siblings

  1. GCN entry · level 0 · unverified · 9ae4971fbc72a790

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 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 23 siblings

  1. GraphConvolution entry · level 1 · ran · 2babbec8f9e467b8

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 1 brick; 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) · 0 unverified. The assembly has not been run end-to-end.

one of 23 siblings

  1. GraphConvolution entry · level 1 · ran · 6a8bc2a8609d02b6

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 1 brick; 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) · 0 unverified. The assembly has not been run end-to-end.

one of 23 siblings

  1. Two_Layer_GCN entry · level 1 · ran · 81656e9a45a5892b

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 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 23 siblings

  1. DAGAD_GCN entry · level 1 · ran · d6b36ad879720430

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 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 23 siblings

  1. GCN entry · level 1 · ran · c58cace7f8be77e2

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

one of 23 siblings

  1. GCNNode entry · level 1 · ran · f57b15b48db1c0bc
  2. Residual helper · level 1 · ran · 1f6d95f2dbf139ad

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 4 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 23 siblings

  1. GraphConvolution entry · level 1 · ran · d42e565640a66336
  2. glorot_init helper · level 0 · unverified · ea40475de51187a2
  3. sparse_dropout helper · level 1 · ran · our draft was wrong · 3df97104adae129f
  4. zeros_init helper · level 0 · unverified · ce80770a1e139cfc

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 23 siblings

  1. GCN entry · level 0 · unverified · 33c9884171e760fd
  2. GCNGP model · level 1 · ran · 7ce73b453b28e799
  3. Linearized_GP helper · level 1 · ran · 086f2aa4471b98ee

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 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 23 siblings

  1. Net entry · level 1 · ran · 8ff00a5cb292d5b8

harvested Assembly for Graph Convolutional Networks (graph method: Graph Convolutional Networks). 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 23 siblings

  1. GraphConv entry · level 1 · ran · b60e4872344aa92f
  1. GCN · 6c29c8b46dcf9b7c · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. GCN · 6cd44dd8e6cefb51 · 4 bricks; individually on a fixture: 0 ran · 4 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. GraphConvolution · 6e4c88ac2f2490f7 · 5 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. InductiveCriticNetwork · 9bb5d3eae19902d5 · 4 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. GCN · b4efcdb26d14b8ca · 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. GraphConvolution · bdc38b6ea4dac0ec · 4 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
  7. GCN · bf3288af44bf3f59 · 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. GraphConvolution · c16c50b4f8c68a8a · 1 brick; 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. GCN · c2b09897fd4a412f · 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. GCN · e9740564569aa978 · 2 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. GCN · eceb463062b8a2ed · 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin

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="1609.02907") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Document ClassificationDrug DiscoveryGeneral ClassificationGraph ClassificationGraph RegressionHeterogeneous Node ClassificationMolecular Property PredictionNode ClassificationNode Classification on Non-Homophilic (Heterophilic) GraphsNode Property PredictionRecommendation SystemsSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification D&D GCN Accuracy 78.151±3.465 #30 of 53 Archive leaderboard report
Graph Classification ENZYMES GCN Accuracy 73.466±4.372 #7 of 54 Archive leaderboard report
Graph Classification IMDb-B GCN Accuracy 79.500±3.109 #9 of 51 Archive leaderboard report
Graph Classification NCI1 GCN Accuracy 84.185±0.644 #22 of 69 Archive leaderboard report
Graph Classification NCI109 GCN Accuracy 83.140±1.248 #13 of 38 Archive leaderboard report
Graph Classification PROTEINS GCN Accuracy 75.536±1.622 #64 of 103 Archive leaderboard report
Graph Property Prediction ogbg-code2 GCN+virtual node Ext. data No #13 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 GCN+virtual node Number of params 12484310 #13 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 GCN+virtual node Test F1 score 0.1595 ± 0.0018 #13 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 GCN+virtual node Validation F1 score 0.1461 ± 0.0013 #13 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 GCN Ext. data No #19 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 GCN Number of params 11033210 #19 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 GCN Test F1 score 0.1507 ± 0.0018 #19 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 GCN Validation F1 score 0.1399 ± 0.0017 #19 of 21 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN Ext. data No #40 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN Number of params 527701 #40 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN Test ROC-AUC 0.7606 ± 0.0097 #40 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN Validation ROC-AUC 0.8204 ± 0.0141 #40 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN+virtual node Ext. data No #41 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN+virtual node Number of params 1978801 #41 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN+virtual node Test ROC-AUC 0.7599 ± 0.0119 #41 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN+virtual node Validation ROC-AUC 0.8384 ± 0.0091 #41 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN (in Julia) Ext. data No #43 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN (in Julia) Number of params 527701 #43 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN (in Julia) Test ROC-AUC 0.7549 ± 0.0163 #43 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molhiv GCN (in Julia) Validation ROC-AUC 0.8042 ± 0.0107 #43 of 43 Archive leaderboard report
Graph Property Prediction ogbg-molpcba GCN+virtual node Ext. data No #30 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba GCN+virtual node Number of params 2017028 #30 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba GCN+virtual node Test AP 0.2424 ± 0.0034 #30 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba GCN+virtual node Validation AP 0.2495 ± 0.0042 #30 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba GCN Ext. data No #36 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba GCN Number of params 565928 #36 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba GCN Test AP 0.2020 ± 0.0024 #36 of 36 Archive leaderboard report
Graph Property Prediction ogbg-molpcba GCN Validation AP 0.2059 ± 0.0033 #36 of 36 Archive leaderboard report
Graph Property Prediction ogbg-ppa GCN+virtual node Ext. data No #17 of 18 Archive leaderboard report
Graph Property Prediction ogbg-ppa GCN+virtual node Number of params 1930537 #17 of 18 Archive leaderboard report
Graph Property Prediction ogbg-ppa GCN+virtual node Test Accuracy 0.6857 ± 0.0061 #17 of 18 Archive leaderboard report
Graph Property Prediction ogbg-ppa GCN+virtual node Validation Accuracy 0.6511 ± 0.0048 #17 of 18 Archive leaderboard report
Graph Property Prediction ogbg-ppa GCN Ext. data No #18 of 18 Archive leaderboard report
Graph Property Prediction ogbg-ppa GCN Number of params 479437 #18 of 18 Archive leaderboard report
Graph Property Prediction ogbg-ppa GCN Test Accuracy 0.6839 ± 0.0084 #18 of 18 Archive leaderboard report
Graph Property Prediction ogbg-ppa GCN Validation Accuracy 0.6497 ± 0.0034 #18 of 18 Archive leaderboard report
Graph Regression ESR2 GCN R2 0.642±0.000 #7 of 9 Archive leaderboard report
Graph Regression ESR2 GCN RMSE 0.528±0.642 #7 of 9 Archive leaderboard report
Graph Regression F2 GCN R2 0.878±0.000 #7 of 9 Archive leaderboard report
Graph Regression F2 GCN RMSE 0.355±0.878 #7 of 9 Archive leaderboard report
Graph Regression KIT GCN R2 0.814±0.000 #7 of 9 Archive leaderboard report
Graph Regression KIT GCN RMSE 0.469±0.814 #7 of 9 Archive leaderboard report
Graph Regression Lipophilicity GCN R2 0.800±0.008 #7 of 23 Archive leaderboard report
Graph Regression Lipophilicity GCN RMSE 0.565±0.011 #7 of 23 Archive leaderboard report
Graph Regression PARP1 GCN R2 0.912±0.000 #7 of 9 Archive leaderboard report
Graph Regression PARP1 GCN RMSE 0.372±0.912 #7 of 9 Archive leaderboard report
Graph Regression PCQM4Mv2-LSC GCN Test MAE 0.1398 #19 of 20 Archive leaderboard report
Graph Regression PCQM4Mv2-LSC GCN Validation MAE 0.1379 #19 of 20 Archive leaderboard report
Graph Regression PGR GCN R2 0.658±0.000 #8 of 9 Archive leaderboard report
Graph Regression PGR GCN RMSE 0.565±0.658 #8 of 9 Archive leaderboard report
Graph Regression ZINC-full GCN Test MAE 0.152±0.023 #19 of 19 Archive leaderboard report
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) GCN Macro-F1 92.17 #5 of 11 Archive leaderboard report
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) GCN Micro-F1 92.12 #5 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) GCN Macro-F1 90.84 #8 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) GCN Micro-F1 91.47 #8 of 11 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) GCN Macro-F1 27.84 #7 of 9 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) GCN Micro-F1 60.23 #7 of 9 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) GCN Macro-F1 57.88 #8 of 11 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) GCN Micro-F1 64.82 #8 of 11 Archive leaderboard report
Link Property Prediction ogbl-citation2 Full-batch GCN Ext. data No #14 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 Full-batch GCN Number of params 296449 #14 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 Full-batch GCN Test MRR 0.8474 ± 0.0021 #14 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 Full-batch GCN Validation MRR 0.8479 ± 0.0023 #14 of 23 Archive leaderboard report
Link Property Prediction ogbl-collab GCN (val as input) Ext. data No #28 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab GCN (val as input) Number of params 296449 #28 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab GCN (val as input) Test Hits@50 0.4714 ± 0.0145 #28 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab GCN (val as input) Validation Hits@50 0.5263 ± 0.0115 #28 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab GCN Ext. data No #30 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab GCN Number of params 296449 #30 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab GCN Test Hits@50 0.4475 ± 0.0107 #30 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab GCN Validation Hits@50 0.5263 ± 0.0115 #30 of 34 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN+JKNet Ext. data No #21 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN+JKNet Number of params 1421571 #21 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN+JKNet Test Hits@20 0.6056 ± 0.0869 #21 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN+JKNet Validation Hits@20 0.6776 ± 0.0095 #21 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN Ext. data No #25 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN Number of params 1289985 #25 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN Test Hits@20 0.3707 ± 0.0507 #25 of 31 Archive leaderboard report
Link Property Prediction ogbl-ddi GCN Validation Hits@20 0.5550 ± 0.0208 #25 of 31 Archive leaderboard report
Link Property Prediction ogbl-ppa GCN Ext. data No #25 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa GCN Number of params 278529 #25 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa GCN Test Hits@100 0.1867 ± 0.0132 #25 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa GCN Validation Hits@100 0.1845 ± 0.0140 #25 of 26 Archive leaderboard report
Molecular Property Prediction ESOL GCN R2 0.936±0.006 #4 of 20 Archive leaderboard report
Molecular Property Prediction ESOL GCN RMSE 0.520±0.024 #4 of 20 Archive leaderboard report
Molecular Property Prediction FreeSolv GCN R2 0.957±0.009 #6 of 22 Archive leaderboard report
Molecular Property Prediction FreeSolv GCN RMSE 0.815±0.086 #6 of 22 Archive leaderboard report
Node Classification Brazil Air-Traffic GCN_cheby (Kipf and Welling, 2017) Accuracy 0.516 #3 of 7 Archive leaderboard report
Node Classification Chameleon (60%/20%/20% random splits) GCN 1:1 Accuracy 64.18 ± 2.62 #20 of 38 Archive leaderboard report
Node Classification CiteSeer (60%/20%/20% random splits) GCN 1:1 Accuracy 81.39 ± 1.23 #16 of 33 Archive leaderboard report
Node Classification Citeseer GCN Accuracy 70.3 #58 of 71 Archive leaderboard report
Node Classification Cora GCN Accuracy 81.5% #61 of 73 Archive leaderboard report
Node Classification Cora (60%/20%/20% random splits) GCN 1:1 Accuracy 87.78 ± 0.96 #20 of 33 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) GCN 1:1 Accuracy 82.46 ± 3.11 #25 of 36 Archive leaderboard report
Node Classification Europe Air-Traffic GCN_cheby (Kipf and Welling, 2017) Accuracy 46.0 #2 of 7 Archive leaderboard report
Node Classification Europe Air-Traffic GCN (Kipf and Welling, 2017) Accuracy 37.1 #6 of 7 Archive leaderboard report
Node Classification Facebook GCN_cheby (Kipf and Welling, 2017) Accuracy 64.6 #5 of 8 Archive leaderboard report
Node Classification Facebook GCN (Kipf and Welling, 2017) Accuracy 57.5 #7 of 8 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) GCN 1:1 Accuracy 35.51 ± 0.99 #30 of 37 Archive leaderboard report
Node Classification Flickr GCN (Kipf and Welling, 2017) Accuracy 0.546 #6 of 8 Archive leaderboard report
Node Classification Flickr GCN_cheby (Kipf and Welling, 2017) Accuracy 0.479 #7 of 8 Archive leaderboard report
Node Classification NELL GCN Accuracy 66.0 #2 of 4 Archive leaderboard report
Node Classification Penn94 GCN Accuracy 82.47 ± 0.27 #15 of 32 Archive leaderboard report
Node Classification PubMed (60%/20%/20% random splits) GCN 1:1 Accuracy 88.9 ± 0.32 #24 of 37 Archive leaderboard report
Node Classification Pubmed GCN Accuracy 79.0 #54 of 70 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) GCN 1:1 Accuracy 44.76 ± 1.39 #23 of 37 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) GCN 1:1 Accuracy 83.11 ± 3.2 #24 of 36 Archive leaderboard report
Node Classification Wiki-Vote GCN_cheby (Kipf and Welling, 2017) Accuracy 49.5 #3 of 6 Archive leaderboard report
Node Classification Wiki-Vote GCN (Kipf and Welling, 2017) Accuracy 32.9 #5 of 6 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) GCN 1:1 Accuracy 75.5 ± 2.92 #26 of 35 Archive leaderboard report
Node Classification genius GCN Accuracy 87.42 ± 0.37 #14 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon(60%/20%/20% random splits) GCN 1:1 Accuracy 64.18 ± 2.62 #17 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (60%/20%/20% random splits) GCN 1:1 Accuracy 82.46 ± 3.11 #25 of 33 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Deezer-Europe GCN 1:1 Accuracy 62.23±0.53 #21 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 GCN 1:1 Accuracy 82.47 ± 0.27 #11 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas(60%/20%/20% random splits) GCN 1:1 Accuracy 83.11 ± 3.2 #22 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin(60%/20%/20% random splits) GCN 1:1 Accuracy 75.5 ± 2.92 #23 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius GCN 1:1 Accuracy 87.42 ± 0.37 #16 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers GCN 1:1 Accuracy 62.18 ± 0.26 #20 of 26 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN+residual+6 layers Ext. data No #54 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN+residual+6 layers Number of params 122542 #54 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN+residual+6 layers Test Accuracy 0.7286 ± 0.0016 #54 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN+residual+6 layers Validation Accuracy 0.7382 ± 0.0007 #54 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN+residual+node2vec Ext. data No #55 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN+residual+node2vec Number of params 21885098 #55 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN+residual+node2vec Test Accuracy 0.7278 ± 0.0013 #55 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN+residual+node2vec Validation Accuracy 0.7414 ± 0.0008 #55 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + 8 layers Ext. data No #59 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + 8 layers Number of params 155824 #59 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + 8 layers Test Accuracy 0.7262 ± 0.0037 #59 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + 8 layers Validation Accuracy 0.7369 ± 0.0021 #59 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN Ext. data No #76 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN Number of params 110120 #76 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN Test Accuracy 0.7174 ± 0.0029 #76 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN Validation Accuracy 0.7300 ± 0.0017 #76 of 86 Archive leaderboard report
Node Property Prediction ogbn-products Full-batch GCN Ext. data No #57 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Full-batch GCN Number of params 103727 #57 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Full-batch GCN Test Accuracy 0.7564 ± 0.0021 #57 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Full-batch GCN Validation Accuracy 0.9200 ± 0.0003 #57 of 64 Archive leaderboard report
Node Property Prediction ogbn-proteins GCN Ext. data No #24 of 26 Archive leaderboard report
Node Property Prediction ogbn-proteins GCN Number of params 96880 #24 of 26 Archive leaderboard report
Node Property Prediction ogbn-proteins GCN Test ROC-AUC 0.7251 ± 0.0035 #24 of 26 Archive leaderboard report
Node Property Prediction ogbn-proteins GCN Validation ROC-AUC 0.7921 ± 0.0018 #24 of 26 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: GCN

GCNGraph Convolutional Networks

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