Papers › Graph Attention Networks

Graph Attention Networks

30 Oct 2017ICLR 2018 1arXiv:1710.10903archive 2025-07-28

Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).

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

No sample from the archive's official repository (PetarV-/GAT) is linked to this paper; the 106 samples below come from 52 community repositories. Syntology harvested code from PetarV-/GAT for another paper.

PetarV-/GAT: 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.

Syntology 106 code samples harvested from 52 repositories linked to this paper: 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. Where Syntology's instrument failed: 8 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): 106 samples from 52 repositories, 61 ran (52 with no instrument failure; 9 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 5 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. 2 of the 61 samples that ran have no recorded date.

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

PetarV-/GAT officialmentioned 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
404nofound/gat mentioned on GitHubpytorchMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
4pygmalion/GAT_tensorflow mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
Anak2016/GAT mentioned on GitHubpytorchMITSyntology: 4 samples, 3 ran (2 instrument-failed) · 1 unverified report
AngusMonroe/GAT-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Anou9531/GAT mentioned on GitHubtfMITSyntology: not harvested report
Aveek-Saha/Graph-Attention-Net mentioned on GitHubtfSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
BIG-S2/keras-gnm mentioned on GitHubSyntology: not harvested report
ChengSashankh/trying-GAT mentioned on GitHubtfMITSyntology: not harvested report
ChengyuSun/gat mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
ColdenChan/GAT_D mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
Diego999/pyGAT mentioned 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
GraphSAINT/GraphSAINT mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
HazyResearch/hgcn mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
HeapHop30/graph-attention-nets mentioned on GitHubtfSyntology: not harvested report
IllinoisGraphBenchmark/IGB-Datasets mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Kaimaoge/IGNNK mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Kristof-Neys/GAT_Neo4j_DGL mentioned on GitHubtfSyntology: not harvested report
Messham87/COVID_GAT mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Negus25/GAT-Mindspore mentioned on GitHubmindsporeSyntology: not harvested report
PumpkinYing/GAT mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
TyngJiunKuo/deep-learning-project mentioned on GitHubtfSyntology: not harvested report
WantingZhao/my_GAT mentioned on GitHubtfMITSyntology: not harvested report
Yindong-Zhang/myGAT mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
YunseobShin/wiki_GAT mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
abhilash1910/GraphAttentionNetworks mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified 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
anish-lu-yihe/SVRT-by-GAT mentioned on GitHubpytorchMITSyntology: not harvested report
arangoml/fastgraphml mentioned on GitHubpytorchSyntology: not harvested report
basiralab/RG-Select mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
basiralab/Reproducible-Generative-Learning mentioned on GitHubpytorchSyntology: not harvested report
blueberryc/pyGAT mentioned on GitHubpytorchMITSyntology: not harvested report
bowu/GraphSearch mentioned on GitHubpytorchSyntology: not harvested report
calciver/Graph-Attention-Networks mentioned on GitHubtfSyntology: not harvested report
danielegrattarola/keras-gat mentioned on GitHubtfMITSyntology: 1 sample, 0 ran · 1 unverified report
davidpicard/homm mentioned on GitHubpytorchSyntology: 13 samples, 2 ran (2 instrument-failed) · 11 unverified report
dmeoli/neuro-sat mentioned on GitHubMITSyntology: not harvested report
ds4dm/sGat mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
ds4dm/sparse-gcn mentioned on GitHubpytorchMITSyntology: not harvested report
dzb1998/pyGAT mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
fanzhenliu/dagad mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
fongyk/graph-attention mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
galkampel/HyperNetworks mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
gayanku/FDGATII mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
gcucurull/jax-gat mentioned on GitHubjaxSyntology: 4 samples, 3 ran (3 instrument-failed) · 1 unverified report
giuseppefutia/link-prediction-code mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
gmum/umwpl2021 mentioned on GitHubSyntology: not harvested report
gordicaleksa/pytorch-GAT mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
handasontam/GAT-with-edgewise-attention mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
isotlaboratory/ml4vrp mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
joaopedromattos/gnee mentioned on GitHubpytorchMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
liu6zijian/simplified-gcn-model mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
marble0117/GNN_models_pytorch mentioned on GitHubpytorchMITSyntology: 2 samples, 0 ran · 2 unverified report
marble0117/GNN_models_pytorch_geometric mentioned on GitHubpytorchMITSyntology: not harvested report
marblet/GNN_models_pytorch_geometric mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
marblet/gat-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
meliketoy/graph-cnn.pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
mitya8128/experiments_notes mentioned on GitHubSyntology: not harvested report
mlzxzhou/keras-gnm mentioned on GitHubSyntology: not harvested report
nnaakkaaii/g2-MLP mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
noahtren/Graph-Attention-Networks-TensorFlow-2 mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
pengsl-lab/mssl mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
pengsl-lab/mssl2drug mentioned on GitHubpytorchSyntology: not harvested report
qema/orca-py mentioned on GitHubpytorchSyntology: not harvested report
shenweichen/GraphNeuralNetwork mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
shi27feng/transformers.satisfy mentioned on GitHubpytorchSyntology: not harvested report
snowkylin/gnn mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
snownus/COOP mentioned on GitHubSyntology: not harvested report
subercui/pyGConvAT mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
taishan1994/pytorch_gat mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
tatp22/pytorch-fast-GAT mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
tlmakinen/GAT-noise mentioned on GitHubpytorchSyntology: not harvested report
vailatuts/SSFG-regularization mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
wan2000/mc-mot mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
weiyangfb/PyTorchSparseGAT mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
whut2962575697/gat_sementic_segmentation mentioned on GitHubpytorchMITSyntology: 6 samples, 4 ran (1 instrument-failed) · 2 unverified report
ydzhang-stormstout/HAT mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
yururyuru00/GAT_pyG mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
zhangbo2008/GAT_network mentioned on GitHubpytorchMITSyntology: not harvested report
zhanglab-aim/cancer-net mentioned on GitHubpytorchGPL-2.0Syntology: not harvested report
zhao-tong/GNNs-easy-to-use mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
zxhhh97/ABot mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Mind23-2/MindCode-4 mindsporeSyntology: not harvested report
MindSpore-scientific-2/code-4 mindsporeSyntology: not harvested report
ak24watch/Graph-Deeplearning-GAT pytorchMITSyntology: 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
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
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
lukecavabarrett/pna pytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

106 samples harvested: 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. “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
2ran · violated contract
8ran · our draft was wrong
1ran; the contract check could not run
49ran
45unverified

Licence: 46 of the 106 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 52 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”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

404nofound/gat community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
adj_to_bias utils/process.py ran MIT (permissive) · 5a0b371866f14f67 · report fixture: signature adj:ndarray/3/float, sizes:ndarray/1/int, nhood:int/0/int · returned ndarray · level recorded 2026-09-25
dfs_split utils/process_ppi.py ran MIT (permissive) · fa7f6abbe630e912 · report fixture: signature adj:csr_matrix/2/int · returned ndarray · level recorded 2026-09-25
parse_index_file in 54 papers utils/process.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · c1d6392f89c5e495 · report fixture: signature filename:str/0/str · returned list · level recorded, date not recorded
sample_mask in 39 papers
census: 4 implementations from 5 papers, 4 distinct outputs on one shared input
utils/process.py ran · violated contract fingerprinted MIT (permissive) · b32fd748b4bbe3bf · report fixture: signature idx:int/0/int, l:int/0/int · returned ndarray · level recorded 2026-09-22
test in 377 papers utils/process_ppi.py ran MIT (permissive) · cbd09a8688d1836a · report fixture: signature adj:csr_matrix/2/int, mapping:list/1/int · returned bool · level recorded 2026-09-25
find_split utils/process_ppi.py unverified MIT (permissive) · 6beddb1e8d4bd5ff · report
4pygmalion/GAT_tensorflow community (archive-listed) 1 sample, 0 ran · 1 unverified
GraphAttentionLayer in 11 papers GAT/_model.py unverified no licence file found · pointer only · c2cadcfe69abfe1c · report
Anak2016/GAT community (archive-listed) 4 samples, 3 ran (2 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
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
make_dot in 11 papers visualize_graph.py ran MIT (permissive) · bca7f86b2fb5bf67 · report fixture: signature var:Tensor/0/float, params:dict/0/? · returned Digraph · level recorded 2026-09-24
normalize_adj in 55 papers utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · d45f434d25f2e870 · report fixture: signature mx:csr_matrix/2/float · returned csc_matrix · level recorded, date not recorded
load_data in 700 papers utils.py unverified MIT (permissive) · c10da56a392c8053 · report
AngusMonroe/GAT-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphAttentionLayer in 11 papers layers.py ran MIT (permissive) · bfd816be65963aae · report fixture: returned GraphAttentionLayer · level recorded 2026-09-22
Aveek-Saha/Graph-Attention-Net community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
gat.py ran MIT (permissive) · ea7e984b0e2dc3d2 · report fixture: returned Attention · level recorded 2026-09-22
GraphAttentionLayer in 11 papers gat.py ran MIT (permissive) · 2b7d556bf1ddeea2 · report fixture: returned GraphAttentionLayer · level recorded 2026-09-22
ChengyuSun/gat community (archive-listed) 1 sample, 0 ran · 1 unverified
load_data in 700 papers utils.py unverified MIT (permissive) · a043edcfa5bf7c76 · report
ColdenChan/GAT_D community (archive-listed) 2 samples, 0 ran · 2 unverified
BaseGAttN models/gat.py unverified MIT (permissive) · ed5c43f164ad0b54 · report
GAT in 16 papers models/gat.py unverified MIT (permissive) · 8e9b126f3a88cbdd · report
GraphSAINT/GraphSAINT community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
AttentionAggregator graphsaint/pytorch_version/layers.py ran · metamorphic tier: deterministic MIT (permissive) · a17fe9c7a3d566f4 · report fixture: returned AttentionAggregator · level recorded 2026-09-22
HazyResearch/hgcn community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
SpGraphAttentionLayer layers/att_layers.py ran · metamorphic tier: deterministic no licence file found · pointer only · f2e88290d89e5830 · report fixture: returned SpGraphAttentionLayer · level recorded 2026-09-22
SpecialSpmmFunction layers/att_layers.py ran no licence file found · pointer only · 3e9e9056af401802 · report fixture: returned SpecialSpmmFunction · level recorded 2026-09-22
SpecialSpmm layers/att_layers.py unverified no licence file found · pointer only · 499f87bed1d30f44 · report
Kaimaoge/IGNNK community (archive-listed) 1 sample, 0 ran · 1 unverified
GAT in 16 papers basic_structure.py unverified no licence file found · pointer only · fb04b1d471c6acc1 · report
Messham87/COVID_GAT community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphAttentionLayer in 11 papers layers.py ran MIT (permissive) · 4830f24ef485057f · report fixture: returned GraphAttentionLayer · level recorded 2026-09-22
Yindong-Zhang/myGAT community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
BaseGraphAttentionLayer layers.py ran MIT (permissive) · 3db162112d63db34 · report fixture: returned BaseGraphAttentionLayer · level recorded 2026-09-22
GraphAttentionLayer in 11 papers layers.py ran MIT (permissive) · deefaca543b8cc51 · report fixture: returned GraphAttentionLayer · level recorded 2026-09-22
GraphConvolutionLayer in 7 papers layers.py ran fingerprinted MIT (permissive) · 1dbf66eba24dbc7e · report fixture: signature feat:Tensor/2/float, adj:Tensor/2/float · returned NoneType · level recorded 2026-09-24
YunseobShin/wiki_GAT community (archive-listed) 1 sample, 0 ran · 1 unverified
GraphAttention in 5 papers keras_gat/graph_attention_layer.py unverified MIT (permissive) · 89ba00d981eb9302 · report
abhilash1910/GraphAttentionNetworks community (archive-listed) 1 sample, 0 ran · 1 unverified
GraphAttention in 5 papers GraphAttentionNetworks/GraphMultiheadAttention.py unverified licence not identified · pointer only · 5e93c4b4d21d5d71 · report
basiralab/RG-Select community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphAttentionLayer in 11 papers models_gat.py ran no licence file found · pointer only · 7de5ed842bb1f8ae · report fixture: returned GraphAttentionLayer · level recorded 2026-09-22
danielegrattarola/keras-gat community (archive-listed) 1 sample, 0 ran · 1 unverified
load_data in 700 papers keras_gat/utils.py unverified MIT (permissive) · 976ef4bf64ce0be7 · report
davidpicard/homm community (archive-listed) 13 samples, 2 ran (2 instrument-failed) · 11 unverified
full_mask_mixer src/model/network/gnn_layers.py ran · our draft was wrong no licence file found · pointer only · 18df0c54b9715ca4 · report fixture: signature h:Tensor/3/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-22
mask_mixer src/model/network/gnn_layers.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 7c2fe0a109d8552e · report fixture: signature h:Tensor/3/float, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GAT_HOMM_Network src/model/network/gnn_layers.py unverified no licence file found · pointer only · 2f96875be1432954 · report
HoM src/model/network/gnn_layers.py unverified no licence file found · pointer only · c752223c4cff0254 · report
HoMLayer src/model/network/gnn_layers.py unverified no licence file found · pointer only · 7c99ecc825b89cb9 · report
HoMLayer_gnn src/model/network/gnn_layers.py unverified no licence file found · pointer only · 7d4a66310b01ccfe · report
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
src/model/network/gnn_layers.py unverified no licence file found · pointer only · 5c5300f98cecf9cc · report
high_order_aggregation_ src/model/network/gnn_layers.py unverified no licence file found · pointer only · afe74d2db9b18ca4 · report
high_order_selection_ src/model/network/gnn_layers.py unverified no licence file found · pointer only · 0a4305f7b4b34882 · report
hom src/model/network/gnn_layers.py unverified no licence file found · pointer only · 87047d4b8762a1c3 · report
po2 src/model/network/gnn_layers.py unverified no licence file found · pointer only · 9001a106b75860f4 · report
po3 src/model/network/gnn_layers.py unverified no licence file found · pointer only · 0f67c084fcf7537d · report
po4 src/model/network/gnn_layers.py unverified no licence file found · pointer only · 71e010ae9e308364 · report
ds4dm/sGat community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
matmul in 24 papers sgcn/masked/functions.py ran MIT (permissive) · cb6188faef06c446 · report fixture: signature indices:Tensor/2/int, values:Tensor/1/float, size:Size/1/int, B:Tensor/2/float · returned Tensor · level recorded 2026-09-26
matmulmasked sgcn/masked/functions.py ran MIT (permissive) · 8d9b7d17ab1ab2c1 · report fixture: signature A:Tensor/2/float, B:Tensor/2/float, indices:tuple/1/Tensor · returned Tensor · level recorded 2026-09-26
dzb1998/pyGAT community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphAttentionLayer in 11 papers layers.py ran · metamorphic tier: invariant MIT (permissive) · 81f6c5575edeb0bf · report fixture: signature input:Tensor/2/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-22
fanzhenliu/dagad community (archive-listed) 1 sample, 0 ran · 1 unverified
DAGAD_GAT DAGAD.py unverified MIT (permissive) · b44bbad1c454ebf4 · report
fongyk/graph-attention community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphAttentionLayer in 11 papers layer.py ran no licence file found · pointer only · d1505ed1f609826b · report fixture: signature global_feature:Tensor/2/float, nodes:list/1/int, neighbors_list:list/1/set · returned Tensor · level recorded 2026-09-24
galkampel/HyperNetworks community (archive-listed) 1 sample, 0 ran · 1 unverified
HyperGATConv model/gat.py unverified no licence file found · pointer only · fc520c658083198c · report
gayanku/FDGATII community (archive-listed) 1 sample, 0 ran · 1 unverified
GraphConvolution_G models.py unverified MIT (permissive) · 5f34746d6309d7fe · report
gcucurull/jax-gat community (archive-listed) 4 samples, 3 ran (3 instrument-failed) · 1 unverified
Dropout in 8 papers models.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5afc838eec40772e · report fixture: signature rate:float/0/float · returned tuple · level recorded 2026-09-22
GraphAttentionLayer in 11 papers models.py ran · our draft was wrong fingerprinted no licence file found · pointer only · aaafc660d13f4e16 · report fixture: signature out_dim:int/0/int, dropout:float/0/float, residual:bool/0/bool · returned tuple · level recorded 2026-09-22
MultiHeadLayer models.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5a977055a872edd8 · report fixture: signature nheads:int/0/int, nhid:int/0/int, dropout:float/0/float, residual:bool/0/bool, last_layer:bool/0/bool · returned tuple · level recorded 2026-09-22
GAT in 16 papers models.py unverified no licence file found · pointer only · 628b8816e46fa27f · report
giuseppefutia/link-prediction-code community (archive-listed) 4 samples, 3 ran (1 instrument-failed) · 1 unverified
GATLayer in 5 papers net.py ran no licence file found · pointer only · 52e34cb027943420 · report fixture: returned GATLayer · level recorded 2026-09-22
NodeApplyModule net.py ran no licence file found · pointer only · debb79dfd7fbb165 · report fixture: returned NodeApplyModule · level recorded 2026-09-22
gat_msg net.py ran · our draft was wrong no licence file found · pointer only · 6083fea83bb7098c · report fixture: signature edge:MockEdgeData/0/? · returned dict · level recorded 2026-09-22
gat_reduce net.py unverified no licence file found · pointer only · 9dc615acb2d8de00 · report
gordicaleksa/pytorch-GAT community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
GATLayer in 5 papers models/definitions/GAT.py ran · metamorphic tier: deterministic MIT (permissive) · 5d5e29ef042a08a8 · report fixture: returned GATLayer · level recorded 2026-09-22
GATLayerImp3 models/definitions/GAT.py ran · metamorphic tier: deterministic MIT (permissive) · 21ba3ceb8353096e · report fixture: returned GATLayerImp3 · level recorded 2026-09-22
LayerType models/definitions/GAT.py unverified MIT (permissive) · dcd585593f9c47a5 · report
handasontam/GAT-with-edgewise-attention community (archive-listed) 2 samples, 0 ran · 2 unverified
BaseGAttN models/gat.py unverified MIT (permissive) · 33f413c8515b4a54 · report
GAT in 16 papers models/gat.py unverified MIT (permissive) · be71c975b356bf8f · report
isotlaboratory/ml4vrp community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GAT in 16 papers modules/layers.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0543c5506767fe53 · report fixture: returned GAT · level recorded 2026-09-22
joaopedromattos/gnee community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
encode_onehot_dict utils.py ran fingerprinted MIT (permissive) · 1562c6eb2b599cd7 · report fixture: signature labels:list/1/str · returned dict · level recorded 2026-09-26
process_event_dataset_from_networkx event_graph_utils.py ran MIT (permissive) · 588bba8cc8a33264 · report fixture: signature G:Graph/0/?, features_attr:str/0/str · returned tuple · level recorded 2026-09-26
cora_networkx utils.py unverified MIT (permissive) · f52a4f3483c697c3 · report
regularization in 12 papers event_graph_utils.py unverified MIT (permissive) · 725414c560fb8a82 · report
liu6zijian/simplified-gcn-model community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
attention_layer in 9 papers gat.py ran no licence file found · pointer only · 6ece140d37c4f3d6 · report fixture: signature x:Tensor/2/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-24
gat_model gat.py ran no licence file found · pointer only · 710685ce65391a79 · report fixture: signature x:Tensor/3/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-24
marble0117/GNN_models_pytorch community (archive-listed) 2 samples, 0 ran · 2 unverified
get_planetoid_dataset datasets.py unverified MIT (permissive) · be1dbf9aac65198d · report
mask_features models/masked_gcn.py unverified MIT (permissive) · 017f3d425a9cd13e · report
marblet/GNN_models_pytorch_geometric community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GAT in 16 papers models/gat.py ran · metamorphic tier: deterministic MIT (permissive) · ef36abf2c8ed6532 · report fixture: returned GAT · level recorded 2026-09-22
marblet/gat-pytorch community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
GAT in 16 papers gat.py ran MIT (permissive) · 14b29bb3c2e77060 · report fixture: returned GAT · level recorded 2026-09-22
GATConv gat.py ran MIT (permissive) · 600d032886c740f2 · report fixture: returned GATConv · level recorded 2026-09-22
meliketoy/graph-cnn.pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
GraphAttention in 5 papers layers.py unverified MIT (permissive) · 5ef6599b549742dd · report
nnaakkaaii/g2-MLP community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GATNode gnn/src/models/networks/gat_node.py ran MIT (permissive) · 3b5dfe5f6487483a · report fixture: returned GATNode · level recorded 2026-09-22
noahtren/Graph-Attention-Networks-TensorFlow-2 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphAttention in 5 papers gat.py ran MIT (permissive) · 3bd3e21f7881b3ad · report fixture: returned GraphAttention · level recorded 2026-09-22
pengsl-lab/mssl community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphAttentionLayer in 11 papers MSSL/models/layers.py ran · metamorphic tier: deterministic no licence file found · pointer only · ef1e2b2dc826e35c · report fixture: returned GraphAttentionLayer · level recorded 2026-09-22
shenweichen/GraphNeuralNetwork community (archive-listed) 1 sample, 0 ran · 1 unverified
GATLayer in 5 papers gnn/gat.py unverified MIT (permissive) · bd896967c973d652 · report
snowkylin/gnn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GATLayer in 5 papers gnn.py ran no licence file found · pointer only · 084e19b084167399 · report fixture: returned GATLayer · level recorded 2026-09-22
subercui/pyGConvAT community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GraphAttentionLayer in 11 papers layers.py ran · metamorphic tier: deterministic MIT (permissive) · 2b9d25ebc1ad21fe · report fixture: returned GraphAttentionLayer · level recorded 2026-09-22
taishan1994/pytorch_gat community (archive-listed) 1 sample, 0 ran · 1 unverified
GAT in 16 papers model.py unverified no licence file found · pointer only · ca3843aa2d3c4206 · report
tatp22/pytorch-fast-GAT community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
GraphAttentionLayer in 11 papers fast_gat/GAT.py ran MIT (permissive) · 5ae6f08a8fb439cf · report fixture: signature nodes:Tensor/2/float, edges:dict/0/? · returned Tensor · level recorded 2026-09-24
GraphAttentionNetwork fast_gat/GAT.py ran MIT (permissive) · 0426746ace37676b · report fixture: signature nodes:Tensor/2/float, edges:dict/0/? · returned Tensor · level recorded 2026-09-24
GraphAttentionHead fast_gat/GAT.py unverified MIT (permissive) · 01569d1c8b54aedd · report
vailatuts/SSFG-regularization community (archive-listed) 2 samples, 0 ran · 2 unverified
CustomGATHeadLayer layers/gat_layer.py unverified licence not identified · pointer only · 550882cf5406f142 · report
CustomGATLayer layers/gat_layer.py unverified licence not identified · pointer only · 69bb60470be073ba · report
wan2000/mc-mot community (archive-listed) 1 sample, 0 ran · 1 unverified
StructuralAttentionLayer stgat/layers.py unverified no licence file found · pointer only · 2e935d44457aab07 · report
weiyangfb/PyTorchSparseGAT community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
GAT in 16 papers models.py ran · metamorphic tier: invariant MIT (permissive) · 605946bfc2bfb229 · report fixture: signature x:Tensor/2/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GraphAttentionLayer in 11 papers models.py ran · metamorphic tier: invariant MIT (permissive) · a1460d4df9be2ad5 · report fixture: signature input:Tensor/2/float, adj:Tensor/2/float · returned Tensor · level recorded 2026-09-22
whut2962575697/gat_sementic_segmentation community (archive-listed) 6 samples, 4 ran (1 instrument-failed) · 2 unverified
GET_BLOCKS in 9 papers roi_pooling/functions/roi_pooling.py ran · violated contract fingerprinted MIT (permissive) · c5acf386fe00c470 · report fixture: signature N:int/0/int · returned int · level recorded 2026-09-22
group_norm in 17 papers layers.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · df538da77a5d06bd · report fixture: signature input:Tensor/4/float, group:int/0/int, running_mean:Tensor/1/float, running_var:Tensor/1/float, weight:Tensor/1/float, bias:Tensor/1/float, use_input_stats:bool/0/bool, momentum:float/0/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
roi_pooling_2d_pytorch roi_pooling/functions/roi_pooling.py ran MIT (permissive) · 1e557c37f1d14adf · report fixture: signature input:Tensor/4/float, rois:Tensor/2/float, output_size:tuple/1/int, spatial_scale:float/0/float · returned Tensor · level recorded 2026-09-26
setup_logger in 122 papers utils.py ran MIT (permissive) · d465a0df5a49343f · report fixture: signature name:str/0/str, save_dir:str/0/str, distributed_rank:int/0/int, train:bool/0/bool · returned Logger · level recorded 2026-09-26
Dtype in 7 papers roi_pooling/utils.py unverified MIT (permissive) · a71b339ad4cd268f · report
roi_pooling_2d roi_pooling/functions/roi_pooling.py unverified MIT (permissive) · 94585c35bb20a736 · report
ydzhang-stormstout/HAT community (archive-listed) 2 samples, 0 ran · 2 unverified
BaseHGAttN models/sp_prod_mhat.py unverified no licence file found · pointer only · b63d599a318b4057 · report
SpMHGAT models/sp_prod_mhat.py unverified no licence file found · pointer only · b5b7966d6d562760 · report
yururyuru00/GAT_pyG community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GATNet models.py ran · metamorphic tier: invariant no licence file found · pointer only · ee89af6272fb3b86 · report fixture: signature x:Tensor/2/float, edge_index:Tensor/2/int · returned Tensor · level recorded 2026-09-22
zhao-tong/GNNs-easy-to-use community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GATLayer in 5 papers GNNs.py ran no licence file found · pointer only · 2e1cd02fdff09cfc · report fixture: returned GATLayer · level recorded 2026-09-22
zxhhh97/ABot community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
getpid scorelist.py ran MIT (permissive) · 6e566909474e4531 · report fixture: signature _:NoneType/0/? · returned int · level recorded 2026-09-26
labmlai/annotated_deep_learning_paper_implementations community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
GAT in 16 papers labml_nn/graphs/gat/experiment.py ran MIT (permissive) · 1d632b6bedff39f7 · report fixture: returned GAT · level recorded 2026-09-22
GraphAttentionLayer in 11 papers labml_nn/graphs/gat/experiment.py ran MIT (permissive) · f133a4cc58a34a5b · report fixture: returned GraphAttentionLayer · level recorded 2026-09-22
lukecavabarrett/pna community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
GATHead models/pytorch/gat/layer.py ran · metamorphic tier: deterministic MIT (permissive) · 9b65469bbd07b3db · report fixture: returned GATHead · level recorded 2026-09-22
GATLayer in 5 papers models/pytorch/gat/layer.py ran MIT (permissive) · 50fe8f71c8211753 · report fixture: returned GATLayer · 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.

44 assemblies on this paper: 44 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

44 sibling assemblies for Graph Attention Networks (GATs) (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 44 sibling assemblies; the other 32 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 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 44 siblings

  1. SpGraphAttentionLayer entry · level 1 · ran · f2e88290d89e5830
  2. SpecialSpmm helper · level 0 · unverified · 499f87bed1d30f44
  3. SpecialSpmmFunction helper · level 1 · ran · 3e9e9056af401802

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 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 44 siblings

  1. GATLayerImp3 entry · level 1 · ran · 21ba3ceb8353096e
  2. GATLayer helper · level 1 · ran · 5d5e29ef042a08a8
  3. LayerType helper · level 0 · unverified · dcd585593f9c47a5

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

one of 44 siblings

  1. GraphAttention entry · level 0 · unverified · 5ef6599b549742dd

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 44 siblings

  1. GAT entry · level 0 · unverified · 8e9b126f3a88cbdd
  2. BaseGAttN helper · level 0 · unverified · ed5c43f164ad0b54

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 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 44 siblings

  1. GAT entry · level 1 · ran · 0543c5506767fe53

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 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 44 siblings

  1. GATLayer entry · level 1 · ran · 50fe8f71c8211753
  2. GATHead helper · level 1 · ran · 9b65469bbd07b3db

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 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 44 siblings

  1. GAT entry · level 1 · ran · ef36abf2c8ed6532

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 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 44 siblings

  1. GATLayer entry · level 1 · ran · 084e19b084167399

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 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 44 siblings

  1. AttentionAggregator entry · level 1 · ran · a17fe9c7a3d566f4

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 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 44 siblings

  1. GraphAttentionLayer entry · level 1 · ran · ef1e2b2dc826e35c

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 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 44 siblings

  1. GraphAttentionLayer entry · level 1 · ran · 2b9d25ebc1ad21fe

harvested Assembly for Graph Attention Networks (GATs) (graph method: Graph Attention Networks (GATs)). 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 44 siblings

  1. GAT entry · level 1 · ran · 14b29bb3c2e77060
  2. GATConv model · level 1 · ran · 600d032886c740f2
  1. GATNode · 629239bdf72434d4 · 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 · assemblies[12] in the JSON twin
  2. GAT · 71e0da22858fec3a · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. CustomGATLayer · 744503198745d3cc · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. GAT · 7615c10688a2c1f7 · 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 · assemblies[15] in the JSON twin
  5. GraphAttention · 7cb27231a3b4b1a7 · 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 · assemblies[16] in the JSON twin
  6. GraphAttentionLayer · 83a249c080779876 · 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 · assemblies[17] in the JSON twin
  7. GraphAttentionLayer · 98481af5e742f0f3 · 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. SpMHGAT · 98af3f0f75e1e1ef · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. GAT · 9df756d0a3aa5b02 · 4 bricks; individually on a fixture: 3 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; 3 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. GATLayer · 9ff236658b1cb2f1 · 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 · assemblies[21] in the JSON twin
  11. GATLayer · a22832cf566c81a3 · 4 bricks; individually on a fixture: 3 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; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
  12. GAT · a57858ef3cdc8bda · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. StructuralAttentionLayer · ac217b2dbeb06b1e · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
  14. HyperGATConv · ad6d62a394f95785 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[25] in the JSON twin
  15. GraphAttentionLayer · ad948e5630cf2918 · 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 · assemblies[26] in the JSON twin
  16. GraphAttentionLayer · aeaecaa6e478a2d9 · 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 · assemblies[27] in the JSON twin
  17. GraphAttentionLayer · b0ac5d5a91665a3e · 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 · assemblies[28] in the JSON twin
  18. GAT · bc4ff4b04638c89a · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[29] in the JSON twin
  19. GraphAttentionLayer · bccceb390a0efc8a · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[30] in the JSON twin
  20. GATNet · be7f642f95506885 · 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[31] in the JSON twin
  21. GraphAttention · c16a09447637da2b · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[32] in the JSON twin
  22. gat_model · cce071df0b2280d3 · 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[33] in the JSON twin
  23. DAGAD_GAT · d034fa2a82a6c858 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[34] in the JSON twin
  24. GAT · d5e8665cafaeb772 · 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[35] in the JSON twin
  25. GAT_HOMM_Network · d6786e913da8ece3 · 13 bricks; individually on a fixture: 2 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; 2 where Syntology's instrument failed) · 11 unverified · The assembly has not been run end-to-end · assemblies[36] in the JSON twin
  26. GATLayer · e228f4614f650890 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[37] in the JSON twin
  27. GAT · e752b781688db95f · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[38] in the JSON twin
  28. GraphAttentionNetwork · ef10896ed0f3e9fb · 3 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[39] in the JSON twin
  29. GraphAttention · f2cdcb21a85752a1 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[40] in the JSON twin
  30. GraphAttentionLayer · f575b1d52c8773af · 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[41] in the JSON twin
  31. GraphConvolution_G · f9a4d9d482a8dd2e · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[42] in the JSON twin
  32. GraphAttentionLayer · fb169a647a0004a0 · 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[43] 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="1710.10903") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Document ClassificationGraph AttentionGraph ClassificationGraph EmbeddingGraph RegressionHeterogeneous Node ClassificationLink PredictionMUlTI-LABEL-ClASSIFICATIONMolecular Property PredictionNode ClassificationNode Classification on Non-Homophilic (Heterophilic) GraphsNode Property PredictionQuestion AnsweringSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Document Classification Cora GAT Accuracy 83.0% #3 of 6 Archive leaderboard report
Graph Classification CIFAR10 100k GAT Accuracy (%) 65.48 #18 of 20 Archive leaderboard report
Graph Classification D&D GAT Accuracy 73.109±3.413 #50 of 53 Archive leaderboard report
Graph Classification ENZYMES GAT Accuracy 78.611±1.556 #3 of 54 Archive leaderboard report
Graph Classification IMDb-B GAT Accuracy 84.250±2.062 #3 of 51 Archive leaderboard report
Graph Classification NCI1 GAT Accuracy 85.109±1.107 #14 of 69 Archive leaderboard report
Graph Classification NCI109 GAT Accuracy 82.560±0.601 #16 of 38 Archive leaderboard report
Graph Classification PROTEINS GAT Accuracy 76.786±1.670 #39 of 103 Archive leaderboard report
Graph Property Prediction ogbg-code2 GAT Ext. data No #16 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 GAT Number of params 11030210 #16 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 GAT Test F1 score 0.1569 ± 0.0010 #16 of 21 Archive leaderboard report
Graph Property Prediction ogbg-code2 GAT Validation F1 score 0.1442 ± 0.0017 #16 of 21 Archive leaderboard report
Graph Regression ESR2 GAT R2 0.666±0.000 #5 of 9 Archive leaderboard report
Graph Regression ESR2 GAT RMSE 0.510±0.666 #5 of 9 Archive leaderboard report
Graph Regression F2 GAT R2 0.886±0.000 #4 of 9 Archive leaderboard report
Graph Regression F2 GAT RMSE 0.343±0.886 #4 of 9 Archive leaderboard report
Graph Regression KIT GAT R2 0.833±0.000 #4 of 9 Archive leaderboard report
Graph Regression KIT GAT RMSE 0.443±0.833 #4 of 9 Archive leaderboard report
Graph Regression Lipophilicity GAT RMSE 0.95 #1 of 1 Archive leaderboard report
Graph Regression Lipophilicity GAT R2 0.820±0.014 #3 of 23 Archive leaderboard report
Graph Regression Lipophilicity GAT RMSE 0.536±0.020 #3 of 23 Archive leaderboard report
Graph Regression PARP1 GAT R2 0.921±0.000 #4 of 9 Archive leaderboard report
Graph Regression PARP1 GAT RMSE 0.353±0.921 #4 of 9 Archive leaderboard report
Graph Regression PGR GAT R2 0.681±0.000 #6 of 9 Archive leaderboard report
Graph Regression PGR GAT RMSE 0.546±0.681 #6 of 9 Archive leaderboard report
Graph Regression ZINC 100k GAT MAE 0.463 #8 of 8 Archive leaderboard report
Graph Regression ZINC-full GAT Test MAE 0.078±0.006 #16 of 19 Archive leaderboard report
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) GAT Macro-F1 92.26 #11 of 11 Archive leaderboard report
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) GAT Micro-F1 92.19 #11 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) GAT Macro-F1 93.83 #11 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) GAT Micro-F1 93.39 #11 of 11 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) GAT Accuracy 65.26 #9 of 9 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) GAT Macro-F1 40.74 #9 of 9 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) GAT Macro-F1 58.94 #11 of 11 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) GAT Micro-F1 64.86 #11 of 11 Archive leaderboard report
Molecular Property Prediction ESOL GAT R2 0.930±0.007 #6 of 20 Archive leaderboard report
Molecular Property Prediction ESOL GAT RMSE 0.540±0.027 #6 of 20 Archive leaderboard report
Molecular Property Prediction FreeSolv GAT R2 0.959±0.011 #5 of 22 Archive leaderboard report
Molecular Property Prediction FreeSolv GAT RMSE 0.791±0.101 #5 of 22 Archive leaderboard report
Node Classification Brazil Air-Traffic GAT (Velickovic et al., 2018) Accuracy 0.382 #7 of 7 Archive leaderboard report
Node Classification Chameleon (60%/20%/20% random splits) GAT 1:1 Accuracy 63.9 ± 0.46 #21 of 38 Archive leaderboard report
Node Classification CiteSeer (0.5%) GAT Accuracy 38.2% #13 of 14 Archive leaderboard report
Node Classification CiteSeer (1%) GAT Accuracy 46.5% #14 of 14 Archive leaderboard report
Node Classification CiteSeer (60%/20%/20% random splits) GAT 1:1 Accuracy 67.20 ± 0.46 #32 of 33 Archive leaderboard report
Node Classification CiteSeer with Public Split: fixed 20 nodes per class GAT Accuracy 72.5 ± 0.7% #27 of 40 Archive leaderboard report
Node Classification Citeseer GAT Accuracy 72.5 ± 0.7% #42 of 71 Archive leaderboard report
Node Classification Citeseer GAT Training Split fixed 20 per node #42 of 71 Archive leaderboard report
Node Classification Citeseer GAT Validation YES #42 of 71 Archive leaderboard report
Node Classification Cora GAT Accuracy 83.0% ± 0.7% #44 of 73 Archive leaderboard report
Node Classification Cora GAT Training Split fixed 20 per node #44 of 73 Archive leaderboard report
Node Classification Cora GAT Validation YES #44 of 73 Archive leaderboard report
Node Classification Cora (0.5%) GAT Accuracy 41.4% #13 of 15 Archive leaderboard report
Node Classification Cora (1%) GAT Accuracy 48.6% #14 of 15 Archive leaderboard report
Node Classification Cora (3%) GAT Accuracy 56.8% #15 of 15 Archive leaderboard report
Node Classification Cora (60%/20%/20% random splits) GAT 1:1 Accuracy 76.70 ± 0.42 #31 of 33 Archive leaderboard report
Node Classification Cora with Public Split: fixed 20 nodes per class GAT Accuracy 83.0 ± 0.7% #23 of 36 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) GAT 1:1 Accuracy 76.00 ± 1.01 #26 of 36 Archive leaderboard report
Node Classification Europe Air-Traffic GAT (Velickovic et al., 2018) Accuracy 42.4 #5 of 7 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) GAT 1:1 Accuracy 35.98 ± 0.23 #28 of 37 Archive leaderboard report
Node Classification Flickr GAT (Velickovic et al., 2018) Accuracy 0.359 #8 of 8 Archive leaderboard report
Node Classification PATTERN 100k GAT Accuracy (%) 75.824 #8 of 9 Archive leaderboard report
Node Classification PPI GAT F1 97.3 #16 of 24 Archive leaderboard report
Node Classification Penn94 GAT Accuracy 81.53 ± 0.55 #19 of 32 Archive leaderboard report
Node Classification PubMed (0.03%) GAT Accuracy 50.9% #12 of 14 Archive leaderboard report
Node Classification PubMed (0.05%) GAT Accuracy 50.4% #13 of 14 Archive leaderboard report
Node Classification PubMed (0.1%) GAT Accuracy 59.6% #13 of 14 Archive leaderboard report
Node Classification PubMed (60%/20%/20% random splits) GAT 1:1 Accuracy 83.28 ± 0.12 #37 of 37 Archive leaderboard report
Node Classification PubMed with Public Split: fixed 20 nodes per class GAT Accuracy 79.0% #23 of 37 Archive leaderboard report
Node Classification Pubmed GAT Accuracy 79.0 ± 0.3% #53 of 70 Archive leaderboard report
Node Classification Pubmed GAT F1-Score 79.0 #53 of 70 Archive leaderboard report
Node Classification Pubmed GAT Training Split fixed 20 per node #53 of 70 Archive leaderboard report
Node Classification Pubmed GAT Validation YES #53 of 70 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) GAT 1:1 Accuracy 42.72 ± 0.33 #24 of 37 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) GAT 1:1 Accuracy 78.87 ± 0.86 #32 of 36 Archive leaderboard report
Node Classification USA Air-Traffic GAT (Velickovic et al., 2018) Accuracy 58.5 #4 of 7 Archive leaderboard report
Node Classification Wiki-Vote GAT (Velickovic et al., 2018) Accuracy 59.4 #2 of 6 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) GAT 1:1 Accuracy 71.01 ± 4.66 #29 of 35 Archive leaderboard report
Node Classification genius GAT Accuracy 55.80 ± 0.87 #25 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon(60%/20%/20% random splits) GAT 1:1 Accuracy 63.9 ± 0.46 #18 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (60%/20%/20% random splits) GAT 1:1 Accuracy 76.00 ± 1.01 #26 of 33 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Deezer-Europe GAT 1:1 Accuracy 61.09±0.77 #22 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 GAT 1:1 Accuracy 81.53 ± 0.55 #14 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Pubmed GAT F1-Score 59.89 ± 4.12 #1 of 1 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Pubmed GAT NMI 55.80 ± 0.87 #1 of 1 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas(60%/20%/20% random splits) GAT 1:1 Accuracy 78.87 ± 0.86 #29 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin(60%/20%/20% random splits) GAT 1:1 Accuracy 71.01 ± 4.66 #26 of 32 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT+label reuse+self KD Ext. data No #25 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT+label reuse+self KD Number of params 1441580 #25 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT+label reuse+self KD Test Accuracy 0.7416 ± 0.0008 #25 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT+label reuse+self KD Validation Accuracy 0.7514 ± 0.0004 #25 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT+label+reuse+topo loss Ext. data No #30 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT+label+reuse+topo loss Number of params 1441580 #30 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT+label+reuse+topo loss Test Accuracy 0.7399 ± 0.0012 #30 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT+label+reuse+topo loss Validation Accuracy 0.7513 ± 0.0009 #30 of 86 Archive leaderboard report
Node Property Prediction ogbn-products GAT with NeighborSampling Ext. data No #48 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GAT with NeighborSampling Number of params 751574 #48 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GAT with NeighborSampling Test Accuracy 0.7945 ± 0.0059 #48 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GAT with NeighborSampling Validation Accuracy Please tell us #48 of 64 Archive leaderboard report
Node Property Prediction ogbn-proteins GAT + labels + node2vec Ext. data No #8 of 26 Archive leaderboard report
Node Property Prediction ogbn-proteins GAT + labels + node2vec Number of params 6360470 #8 of 26 Archive leaderboard report
Node Property Prediction ogbn-proteins GAT + labels + node2vec Test ROC-AUC 0.8711 ± 0.0007 #8 of 26 Archive leaderboard report
Node Property Prediction ogbn-proteins GAT + labels + node2vec Validation ROC-AUC 0.9217 ± 0.0011 #8 of 26 Archive leaderboard report
Skeleton Based Action Recognition J-HMBD Early Action GAT 10% 58.1 #2 of 2 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: GAT

GAT

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