Papers › Modeling Relational Data with Graph Convolutional Networks

Modeling Relational Data with Graph Convolutional Networks

17 Mar 2017arXiv:1703.06103archive 2025-07-28

Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, Max Welling

Knowledge graphs enable a wide variety of applications, including question answering and information retrieval. Despite the great effort invested in their creation and maintenance, even the largest (e.g., Yago, DBPedia or Wikidata) remain incomplete. We introduce Relational Graph Convolutional Networks (R-GCNs) and apply them to two standard knowledge base completion tasks: Link prediction (recovery of missing facts, i.e. subject-predicate-object triples) and entity classification (recovery of missing entity attributes). R-GCNs are related to a recent class of neural networks operating on graphs, and are developed specifically to deal with the highly multi-relational data characteristic of realistic knowledge bases. We demonstrate the effectiveness of R-GCNs as a stand-alone model for entity classification. We further show that factorization models for link prediction such as DistMult can be significantly improved by enriching them with an encoder model to accumulate evidence over multiple inference steps in the relational graph, demonstrating a large improvement of 29.8% on FB15k-237 over a decoder-only baseline.

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

Syntology 32 code samples: 31 from 12 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 32: 18 ran (of which 3 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 26 samples from 11 repositories, 12 ran (7 with no instrument failure; 5 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 3 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.

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

tkipf/relational-gcn officialmentioned on GitHubtfMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
INK-USC/MHGRN mentioned on GitHubpytorchSyntology: not harvested report
INK-USC/RE-Net mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
MichSchli/RelationPrediction mentioned on GitHubtfMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
Microsoft/gated-graph-neural-network-samples mentioned on GitHubtfSyntology: not harvested report
QustKcz/relational-GCN mentioned on GitHubtfSyntology: 4 samples, 2 ran (1 instrument-failed) · 2 unverified report
anilakash/indkgc mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Composition-based Multi-Relational Graph Convolutional Networks (arXiv:1911.03082; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
berlincho/RGCN-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
chalothon/Graph-Convolutional-Networks-for-Relational-Link-Prediction mentioned on GitHubtfMITSyntology: not harvested report
dglai/wsdm2022-challenge mentioned on GitHubpytorchSyntology: not harvested report
giuseppefutia/semi mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
guillaumejaume/tuto-dl-on-graphs mentioned on GitHubpytorchMITSyntology: not harvested report
kracr/document-level-relation-extraction mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
masakicktashiro/rgcn_pytorch_implementation mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
parkererickson/crunchBaseGraph mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
predict-idlab/RR-GCN mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
shijx12/kqapro_baselines mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering... (arXiv:2007.03875; that paper's own run record: 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) · 9 unverified) and ACL Anthology id 2022.findings-emnlp.133 (that paper's own run record: 0 ran · 9 unverified); nothing checks that they implement this paper's method. report
susurrant/flow-imputation mentioned on GitHubtfSyntology: not harvested report
susurrant/spatial-interaction-modeling mentioned on GitHubtfSyntology: 7 samples, 5 ran (3 instrument-failed) · 2 unverified report
thiviyanT/torch-rgcn mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
tkipf/gae mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
toooooodo/rgcn-linkprediction mentioned on GitHubpytorchSyntology: not harvested report
JiabenLi/rgcn_paddlepaddle paddleSyntology: 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
yangyucheng000/Papers 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

32 samples harvested: 18 ran (of which 3 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 14 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
1ran · violated contract
1ran · our draft was wrong
4ran; the contract check could not run
11ran
14unverified

Licence: 15 of the 32 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 12 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “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 1 sample 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.

tkipf/relational-gcn official repository 5 samples, 5 ran (0 instrument-failed) · 0 unverified
csc_zero_cols rgcn/utils.py ran MIT (permissive) · e1a1d86eb911298c · report fixture: signature csc:csc_matrix/2/float, cols_to_zero:ndarray/1/int · returned csc_matrix · level recorded 2026-09-25
csr_zero_rows rgcn/utils.py ran MIT (permissive) · d62c184c10723fda · report fixture: signature csr:csr_matrix/2/float, rows_to_zero:ndarray/1/int · returned csr_matrix · level recorded 2026-09-25
load_sparse_csr in 7 papers rgcn/data_utils.py ran MIT (permissive) · 02de651d9efcfd65 · report fixture: signature filename:str/0/str · returned csr_matrix · level recorded 2026-09-25
parse in 85 papers rgcn/data_utils.py ran fingerprinted MIT (permissive) · 241fcba67ca4a269 · report fixture: signature symbol:str/0/str · returned str · level recorded 2026-09-25
sp_vec_from_idx_list rgcn/utils.py ran MIT (permissive) · 24a38c97cf6b6580 · report fixture: signature idx_list:list/1/int, dim:int/0/int · returned csr_matrix · level recorded 2026-09-25
INK-USC/RE-Net community (archive-listed) 1 sample, 0 ran · 1 unverified
RGCNLayer RGCN.py unverified no licence file found · pointer only · e1fa7a1467322bab · report
MichSchli/RelationPrediction community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
read in 34 papers code/common/settings_reader.py ran MIT (permissive) · aecde0e9a66b3279 · report fixture: signature filename:str/0/str · returned Settings · level recorded 2026-09-26
read_triplet_file code/common/io.py ran MIT (permissive) · d945735b7bb56f17 · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-26
read_triplets_as_list code/common/io.py ran MIT (permissive) · 536bd3fa07b27fed · report fixture: signature filename:str/0/str, entity_dict:str/0/str, relation_dict:str/0/str · returned list · level recorded 2026-09-26
read_dictionary code/common/io.py unverified MIT (permissive) · 00587b6b3a684969 · report
QustKcz/relational-GCN community (archive-listed) 4 samples, 2 ran (1 instrument-failed) · 2 unverified
Model in 227 papers code/encoders/message_gcns/gcn_basis.py ran MIT (permissive) · e38cd476b8281a12 · report fixture: returned Model · level recorded 2026-09-22
make_tf_variable code/encoders/message_gcns/gcn_basis.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · eee67eafc4b13ee4 · report fixture: signature mean:float/0/float, variance:float/0/float, shape:tuple/1/int, init:str/0/str · returned ResourceVariable · level recorded 2026-09-22
BasisGcn code/encoders/message_gcns/gcn_basis.py unverified MIT (permissive) · 6fc2ea51851a4f5d · report
MessageGcn code/encoders/message_gcns/gcn_basis.py unverified MIT (permissive) · 1560b6e47bad3798 · report
berlincho/RGCN-pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
RelationalGraphConvModel models.py unverified no licence file found · pointer only · 396309e66058552e · report
giuseppefutia/semi community (archive-listed) 1 sample, 0 ran · 1 unverified
RGCNLayer src/link_prediction/layers.py unverified GPL-3.0 (copyleft) · pointer only · aff7c6441824509d · report
kracr/document-level-relation-extraction community (archive-listed) 1 sample, 0 ran · 1 unverified
RGCNConv DocRE-CLiP/code/link prediction/models.py unverified Apache-2.0 (permissive) · b858c1faaadce1a7 · report
masakicktashiro/rgcn_pytorch_implementation community (archive-listed) 1 sample, 0 ran · 1 unverified
GraphConvolution in 36 papers layers.py unverified no licence file found · pointer only · 8d26f1fa141a632b · report
parkererickson/crunchBaseGraph community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
gcn_reduce py_scripts/gcn.py ran · our draft was wrong no licence file found · pointer only · 4e2d70eb57ed4788 · report fixture: signature nodes:MockNodes/0/? · returned dict · level recorded 2026-09-22
GCNLayer in 10 papers py_scripts/gcn.py unverified no licence file found · pointer only · 2bfb21c319767958 · report
gcn_message py_scripts/gcn.py unverified no licence file found · pointer only · a8e4cdc01a9f23a6 · report
susurrant/spatial-interaction-modeling community (archive-listed) 7 samples, 5 ran (3 instrument-failed) · 2 unverified
Model in 227 papers SI-GCN/code/encoders/message_gcns/gcn_basis.py ran no licence file found · pointer only · 2c3abf305bb94378 · report fixture: returned Model · level recorded 2026-09-22
dot_or_lookup SI-GCN/code/encoders/message_gcns/gcn_basis.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · d8d50ae992bdb3c9 · report fixture: signature features:EagerTensor/1/int, weights:EagerTensor/2/float, onehot_input:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
glorot_variance SI-GCN/code/encoders/message_gcns/gcn_basis.py ran · violated contract fingerprinted no licence file found · pointer only · a9a4285637586425 · report fixture: signature shape:tuple/1/int · returned float64 · level recorded 2026-09-22
make_tf_bias SI-GCN/code/encoders/message_gcns/gcn_basis.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted no licence file found · pointer only · 2ff4c1185681f679 · report fixture: signature shape:tuple/1/int, init:int/0/int · returned ResourceVariable · level recorded 2026-09-22
make_tf_variable SI-GCN/code/encoders/message_gcns/gcn_basis.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · ce564e1ae279d09c · report fixture: signature mean:float/0/float, variance:float/0/float, shape:tuple/1/int, var_name:str/0/str, init:str/0/str · returned ResourceVariable · level recorded 2026-09-22
BasisGcn SI-GCN/code/encoders/message_gcns/gcn_basis.py unverified no licence file found · pointer only · 7e784123e5ac077d · report
MessageGcn SI-GCN/code/encoders/message_gcns/gcn_basis.py unverified no licence file found · pointer only · c0687ad3ab3730c9 · report
thiviyanT/torch-rgcn community (archive-listed) 1 sample, 0 ran · 1 unverified
RelationalGraphConvolutionNC torch_rgcn/layers.py unverified MIT (permissive) · c746dc3cd7142fb7 · report
tkipf/gae community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
Layer in 20 papers gae/layers.py ran fingerprinted MIT (permissive) · c101076233bfcdee · report fixture: returned Layer · level recorded 2026-09-22
GraphConvolution in 36 papers gae/layers.py unverified MIT (permissive) · c97818a941d8a0b9 · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
get_layer_uid in 30 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · addac9c28c065096 · report fixture: signature layer_name:str/0/str · returned int · 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.

10 assemblies on this paper: 10 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

10 sibling assemblies for Relational Graph Convolutional Networks (R-GCNs) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Relational Graph Convolutional Networks (R-GCNs) (graph method: Relational Graph Convolutional Networks (R-GCNs)). 7 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. BasisGcn entry · level 0 · unverified · 7e784123e5ac077d
  2. MessageGcn model · level 0 · unverified · c0687ad3ab3730c9
  3. dot_or_lookup helper · level 1 · ran; the contract check could not run (RAISES) · d8d50ae992bdb3c9
  4. glorot_variance helper · level 1 · ran · violated contract · a9a4285637586425
  5. make_tf_bias helper · level 1 · ran; the contract check could not run (RAISES) · 2ff4c1185681f679
  6. make_tf_variable helper · level 1 · ran; the contract check could not run (RAISES) · ce564e1ae279d09c
  7. Model helper · level 1 · ran · 2c3abf305bb94378

harvested Assembly for Relational Graph Convolutional Networks (R-GCNs) (graph method: Relational Graph Convolutional Networks (R-GCNs)). 7 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. BasisGcn entry · level 0 · unverified · 6fc2ea51851a4f5d
  2. MessageGcn helper · level 0 · unverified · 1560b6e47bad3798
  3. dot_or_lookup helper · level 1 · ran; the contract check could not run (RAISES) · d8d50ae992bdb3c9
  4. glorot_variance helper · level 1 · ran · violated contract · a9a4285637586425
  5. make_tf_bias helper · level 1 · ran; the contract check could not run (RAISES) · 2ff4c1185681f679
  6. make_tf_variable helper · level 1 · ran; the contract check could not run (RAISES) · eee67eafc4b13ee4
  7. Model helper · level 1 · ran · e38cd476b8281a12

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

one of 10 siblings

  1. RGCNLayer entry · level 0 · unverified · aff7c6441824509d

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

one of 10 siblings

  1. RGCNConv entry · level 0 · unverified · b858c1faaadce1a7

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

one of 10 siblings

  1. GCNLayer entry · level 0 · unverified · 2bfb21c319767958
  2. gcn_message helper · level 0 · unverified · a8e4cdc01a9f23a6
  3. gcn_reduce helper · level 1 · ran · our draft was wrong · 4e2d70eb57ed4788

harvested Assembly for Relational Graph Convolutional Networks (R-GCNs) (graph method: Relational Graph Convolutional Networks (R-GCNs)). 3 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 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.

one of 10 siblings

  1. GraphConvolution entry · level 0 · unverified · c97818a941d8a0b9
  2. Layer helper · level 1 · ran · c101076233bfcdee
  3. get_layer_uid helper · level 1 · ran · honoured contract · addac9c28c065096

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

one of 10 siblings

  1. RelationalGraphConvModel entry · level 0 · unverified · 396309e66058552e

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

one of 10 siblings

  1. RGCNLayer entry · level 0 · unverified · e1fa7a1467322bab

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

one of 10 siblings

  1. GraphConvolution entry · level 0 · unverified · 8d26f1fa141a632b

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

one of 10 siblings

  1. RelationalGraphConvolutionNC entry · level 0 · unverified · c746dc3cd7142fb7

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="1703.06103") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderGeneral ClassificationGraph ClassificationHeterogeneous Node ClassificationInformation RetrievalKnowledge Base CompletionKnowledge GraphsLink PredictionNode ClassificationNode Property PredictionRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) RGCN Macro-F1 91.55 #6 of 11 Archive leaderboard report
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) RGCN Micro-F1 91.41 #6 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) RGCN Macro-F1 91.52 #7 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) RGCN Micro-F1 92.07 #7 of 11 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) RGCN Macro-F1 46.78 #5 of 9 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) RGCN Micro-F1 58.33 #5 of 9 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) RGCN Macro-F1 58.85 #7 of 11 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) RGCN Micro-F1 62.05 #7 of 11 Archive leaderboard report
Heterogeneous Node Classification OAG-L1-Field RGCN MRR 84.92 #4 of 5 Archive leaderboard report
Heterogeneous Node Classification OAG-L1-Field RGCN NDCG 85.91 #4 of 5 Archive leaderboard report
Heterogeneous Node Classification OAG-Venue RGCN MRR 31.51 #3 of 5 Archive leaderboard report
Heterogeneous Node Classification OAG-Venue RGCN NDCG 48.93 #3 of 5 Archive leaderboard report
Node Classification AIFB R-GCN Accuracy 95.83 #1 of 7 Archive leaderboard report
Node Classification AM R-GCN Accuracy 89.29 #4 of 8 Archive leaderboard report
Node Classification BGS R-GCN Accuracy 83.10 #6 of 7 Archive leaderboard report
Node Classification MUTAG R-GCN Accuracy 73.23 #5 of 6 Archive leaderboard report
Node Property Prediction ogbn-mag R-GSN Ext. data No #26 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag R-GSN Number of params 154373028 #26 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag R-GSN Test Accuracy 0.5032 ± 0.0037 #26 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag R-GSN Validation Accuracy 0.5182 ± 0.0041 #26 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag Full-batch R-GCN Ext. data No #34 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag Full-batch R-GCN Number of params 154366772 #34 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag Full-batch R-GCN Test Accuracy 0.3977 ± 0.0046 #34 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag Full-batch R-GCN Validation Accuracy 0.4084 ± 0.0041 #34 of 39 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: RGCN

RGCN

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