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 Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1902.07153")

Code

Syntology Ran 3 of 8 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · our draft was wrong.

By repository: official repository: 8 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Tiiiger/SGC officialmentioned in papermentioned on GitHubpytorchMIT report
changminwu/expandergnn mentioned on GitHubpytorch report
hazdzz/SGC mentioned on GitHubpytorchLGPL-2.1 report
ydtydr/hyla mentioned on GitHubpytorch report
dmlc/dgl pytorch report
dmlc/dgl pytorch report
dmlc/dgl pytorch 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.

Code Syntology ran Syntology

8 samples harvested; 3 ran; 2 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

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

Licence: 0 of the 8 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 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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

accuracy Tiiiger/SGC/metrics.py official repository ran · honoured contract fingerprinted MIT (permissive) · 18557871f0c93b3f · report
parse_index_file Tiiiger/SGC/utils.py official repository ran · honoured contract MIT (permissive) · c1d6392f89c5e495 · report
sparse_mx_to_torch_sparse_tensor Tiiiger/SGC/utils.py official repository ran · our draft was wrong MIT (permissive) · c97b99c4e8201a97 · report
aug_normalized_adjacency Tiiiger/SGC/normalization.py official repository unverified MIT (permissive) · a4a8c0e8d8c8a86e · report
f1 Tiiiger/SGC/metrics.py official repository unverified MIT (permissive) · cc1fd8ffd02dab36 · report
fetch_normalization Tiiiger/SGC/normalization.py official repository unverified MIT (permissive) · cbd567cd870e332a · report
get_model Tiiiger/SGC/models.py official repository unverified MIT (permissive) · c6e6b26c7f2a5617 · report
row_normalize Tiiiger/SGC/normalization.py official repository unverified MIT (permissive) · 9fe90a5693925ebb · report

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