Papers › Simplifying Graph Convolutional Networks

Simplifying Graph Convolutional Networks

19 Feb 2019arXiv:1902.07153archive 2025-07-28

Felix Wu, Tianyi Zhang, Amauri Holanda de Souza Jr., Christopher Fifty, Tao Yu, Kilian Q. Weinberger

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches, and as a result, may inherit unnecessary complexity and redundant computation. In this paper, we reduce this excess complexity through successively removing nonlinearities and collapsing weight matrices between consecutive layers. We theoretically analyze the resulting linear model and show that it corresponds to a fixed low-pass filter followed by a linear classifier. Notably, our experimental evaluation demonstrates that these simplifications do not negatively impact accuracy in many downstream applications. Moreover, the resulting model scales to larger datasets, is naturally interpretable, and yields up to two orders of magnitude speedup over FastGCN.

PaperPDFCodeCode Syntology ran

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 8 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 8 ran (7 with no instrument failure; 1 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

Tiiiger/SGC officialmentioned in papermentioned on GitHubpytorchMITSyntology: 8 samples, 8 ran (1 instrument-failed) · 0 unverified report
changminwu/expandergnn mentioned on GitHubpytorchSyntology: 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
hazdzz/SGC mentioned on GitHubpytorchLGPL-2.1Syntology: not harvested report
ydtydr/hyla mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Random Laplacian Features for Learning with Hyperbolic Space (arXiv:2202.06854; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); 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
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

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

8 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 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.

2ran · honoured contract
1ran · our draft was wrong
5ran

Licence: 2 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 Tiiiger/SGC. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Tiiiger/SGC official repository 8 samples, 8 ran (1 instrument-failed) · 0 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
metrics.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 18557871f0c93b3f · report fixture: signature output:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
aug_normalized_adjacency normalization.py ran MIT (permissive) · a4a8c0e8d8c8a86e · report fixture: signature adj:coo_matrix/2/float · returned coo_matrix · level recorded 2026-09-25
f1 in 57 papers metrics.py ran fingerprinted MIT (permissive) · cc1fd8ffd02dab36 · report fixture: signature output:Tensor/2/float, labels:Tensor/1/int · returned tuple · level recorded 2026-09-25
fetch_normalization normalization.py ran MIT (permissive) · cbd567cd870e332a · report fixture: signature type:str/0/str · returned function · level recorded 2026-09-25
get_model in 368 papers models.py ran MIT (permissive) · c6e6b26c7f2a5617 · report fixture: signature model_opt:str/0/str, nfeat:int/0/int, nclass:int/0/int, nhid:int/0/int, dropout:float/0/float, cuda:bool/0/bool · returned GCN · level recorded 2026-09-25
parse_index_file in 54 papers utils.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
row_normalize in 6 papers normalization.py ran MIT (permissive) · 9fe90a5693925ebb · report fixture: signature mx:csr_matrix/2/float · returned csr_matrix · level recorded 2026-09-25
sparse_mx_to_torch_sparse_tensor in 41 papers utils.py ran · our draft was wrong MIT (permissive) · c97b99c4e8201a97 · report fixture: signature sparse_mx:csr_matrix/2/float · returned Tensor · level recorded 2026-09-22

Tasks

Graph RegressionImage ClassificationNode ClassificationNode Classification on Non-Homophilic (Heterophilic) GraphsRelation ExtractionSentiment AnalysisSkeleton Based Action RecognitionText Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Regression Lipophilicity SGC RMSE 0.998 #20 of 23 Archive leaderboard report
Node Classification Chameleon (60%/20%/20% random splits) SGC-1 1:1 Accuracy 64.86 ± 1.81 #18 of 38 Archive leaderboard report
Node Classification Chameleon (60%/20%/20% random splits) SGC-2 1:1 Accuracy 62.67 ± 2.41 #25 of 38 Archive leaderboard report
Node Classification CiteSeer (60%/20%/20% random splits) SGC-2 1:1 Accuracy 80.75 ± 1.15 #21 of 33 Archive leaderboard report
Node Classification CiteSeer (60%/20%/20% random splits) SGC-1 1:1 Accuracy 79.66 ± 0.75 #24 of 33 Archive leaderboard report
Node Classification Cora (60%/20%/20% random splits) SGC-2 1:1 Accuracy 85.48 ± 1.48 #26 of 33 Archive leaderboard report
Node Classification Cora (60%/20%/20% random splits) SGC-1 1:1 Accuracy 85.12 ± 1.64 #28 of 33 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) SGC-2 1:1 Accuracy 72.62 ± 9.92 #30 of 36 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) SGC-1 1:1 Accuracy 70.98 ± 8.39 #32 of 36 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) SGC-2 1:1 Accuracy 28.81 ± 1.11 #36 of 37 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) SGC-1 1:1 Accuracy 25.26 ± 1.18 #37 of 37 Archive leaderboard report
Node Classification Penn94 SGC 2-hop Accuracy 76.09 ± 0.45 #25 of 32 Archive leaderboard report
Node Classification Penn94 SGC 1-hop Accuracy 66.79 ± 0.27 #31 of 32 Archive leaderboard report
Node Classification PubMed (60%/20%/20% random splits) SGC-1 1:1 Accuracy 85.5 ± 0.76 #33 of 37 Archive leaderboard report
Node Classification PubMed (60%/20%/20% random splits) SGC-2 1:1 Accuracy 85.36 ± 0.52 #34 of 37 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) SGC-1 1:1 Accuracy 47.62 ± 1.27 #18 of 37 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) SGC-2 1:1 Accuracy 41.25 ± 1.4 #27 of 37 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) SGC-1 1:1 Accuracy 83.28 ± 5.43 #23 of 36 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) SGC-2 1:1 Accuracy 81.31 ± 3.3 #28 of 36 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) SGC-2 1:1 Accuracy 74.75 ± 2.89 #28 of 35 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) SGC-1 1:1 Accuracy 70.38 ± 2.85 #30 of 35 Archive leaderboard report
Node Classification genius SGC 1-hop Accuracy 82.36 ± 0.37 #19 of 26 Archive leaderboard report
Node Classification genius SGC 2-hop Accuracy 82.10 ± 0.14 #20 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon(60%/20%/20% random splits) SGC-1 1:1 Accuracy 64.86 ± 1.81 #15 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon(60%/20%/20% random splits) SGC-2 1:1 Accuracy 62.67 ± 2.41 #21 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (60%/20%/20% random splits) SGC-2 1:1 Accuracy 72.62 ± 9.92 #28 of 33 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (60%/20%/20% random splits) SGC-1 1:1 Accuracy 70.98 ± 8.39 #30 of 33 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Deezer-Europe SGC-1 1:1 Accuracy 59.73±0.12 #24 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 SGC 2-hop 1:1 Accuracy 76.09 ± 0.45 #21 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 SGC 1-hop 1:1 Accuracy 66.79 ± 0.27 #27 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas(60%/20%/20% random splits) SGC-1 1:1 Accuracy 83.28 ± 5.43 #21 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas(60%/20%/20% random splits) SGC-2 1:1 Accuracy 81.31 ± 3.3 #26 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin(60%/20%/20% random splits) SGC-2 1:1 Accuracy 74.75 ± 2.89 #25 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin(60%/20%/20% random splits) SGC-1 1:1 Accuracy 70.38 ± 2.85 #27 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius SGC 1-hop 1:1 Accuracy 82.36 ± 0.37 #21 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius SGC 2-hop 1:1 Accuracy 82.10 ± 0.14 #22 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers SGC 2-hop 1:1 Accuracy 59.94 ± 0.21 #25 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers SGC 1-hop 1:1 Accuracy 58.97 ± 0.19 #26 of 26 Archive leaderboard report
Node Property Prediction ogbn-papers100M SGC Ext. data No #18 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SGC Number of params 144044 #18 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SGC Test Accuracy 0.6329 ± 0.0019 #18 of 20 Archive leaderboard report
Node Property Prediction ogbn-papers100M SGC Validation Accuracy 0.6648 ± 0.0020 #18 of 20 Archive leaderboard report
Relation Extraction TACRED C-SGC F1 67.0 #34 of 40 Archive leaderboard report
Sentiment Analysis MR SGC Accuracy 75.9 #17 of 19 Archive leaderboard report
Sentiment Analysis MR SGCN Accuracy 75.9 #18 of 19 Archive leaderboard report
Skeleton Based Action Recognition SBU / SBU-Refine SGCConv Accuracy 94.0% #7 of 9 Archive leaderboard report
Text Classification 20NEWS SGC Accuracy 88.5 #4 of 16 Archive leaderboard report
Text Classification 20NEWS SGCN Accuracy 88.5 #5 of 16 Archive leaderboard report
Text Classification Ohsumed SGCN Accuracy 68.5 #3 of 10 Archive leaderboard report
Text Classification Ohsumed SGC Accuracy 68.5 #4 of 10 Archive leaderboard report
Text Classification R52 SGC Accuracy 94.0 #5 of 8 Archive leaderboard report
Text Classification R52 SGCN Accuracy 94.0 #6 of 8 Archive leaderboard report
Text Classification R8 SGC Accuracy 97.2 #14 of 21 Archive leaderboard report
Text Classification R8 SGCN Accuracy 97.2 #15 of 21 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

FastGCN

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