Papers › Combining Label Propagation and Simple Models Out-performs Graph Neural Networks

Combining Label Propagation and Simple Models Out-performs Graph Neural Networks

27 Oct 2020ICLR 2021 1arXiv:2010.13993archive 2025-07-28

Qian Huang, Horace He, Abhay Singh, Ser-Nam Lim, Austin R. Benson

Graph Neural Networks (GNNs) are the predominant technique for learning over graphs. However, there is relatively little understanding of why GNNs are successful in practice and whether they are necessary for good performance. Here, we show that for many standard transductive node classification benchmarks, we can exceed or match the performance of state-of-the-art GNNs by combining shallow models that ignore the graph structure with two simple post-processing steps that exploit correlation in the label structure: (i) an "error correlation" that spreads residual errors in training data to correct errors in test data and (ii) a "prediction correlation" that smooths the predictions on the test data. We call this overall procedure Correct and Smooth (C&S), and the post-processing steps are implemented via simple modifications to standard label propagation techniques from early graph-based semi-supervised learning methods. Our approach exceeds or nearly matches the performance of state-of-the-art GNNs on a wide variety of benchmarks, with just a small fraction of the parameters and orders of magnitude faster runtime. For instance, we exceed the best known GNN performance on the OGB-Products dataset with 137 times fewer parameters and greater than 100 times less training time. The performance of our methods highlights how directly incorporating label information into the learning algorithm (as was done in traditional techniques) yields easy and substantial performance gains. We can also incorporate our techniques into big GNN models, providing modest gains. Our code for the OGB results is at https://github.com/Chillee/CorrectAndSmooth.

PaperPDFConference PDFCodeCode 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 5 code samples harvested from 2 repositories linked to this paper: 3 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; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 1 ran (1 with no instrument failure; 0 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

CUAI/CorrectAndSmooth officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
Chillee/CorrectAndSmoothOGB mentioned on GitHubpytorchSyntology: not harvested report
sangyx/gtrick mentioned on GitHubpytorchMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
xnuohz/CorrectAndSmooth-dgl mentioned on GitHubpytorchSyntology: not harvested report
ytchx1999/GCN_res-CS-v2 mentioned on GitHubpytorchSyntology: not harvested report
ytchx1999/PyG-GCN_res-CS mentioned on GitHubpytorchSyntology: 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

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

5 samples harvested: 3 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; 2 where Syntology's instrument failed) · 2 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 · our draft was wrong
1ran
2unverified

Licence: 2 of the 5 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

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

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

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

CUAI/CorrectAndSmooth official repository 2 samples, 2 ran (2 instrument-failed) · 0 unverified
test in 377 papers gen_models.py ran · our draft was wrong no licence file found · pointer only · 5a209cddf7b3e52f · report fixture: signature model:callable/0/?, x:Tensor/2/float, y:Tensor/2/int, split_idx:dict/0/?, evaluator:Evaluator/0/? · returned tuple · level recorded 2026-09-22
train in 522 papers gen_models.py ran · our draft was wrong no licence file found · pointer only · fac9425843013f50 · report fixture: signature model:callable/0/?, x:Tensor/2/float, y_true:Tensor/2/int, train_idx:Tensor/1/int, optimizer:Adam/0/? · returned float · level recorded 2026-09-22
sangyx/gtrick community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
random_feature gtrick/random_feature.py ran fingerprinted MIT (permissive) · 95753adaeccb24eb · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
eval in 90 papers benchmark/dgl/graph_pred.py unverified MIT (permissive) · 3f05a96b5815dd82 · report
train in 522 papers benchmark/dgl/graph_pred.py unverified MIT (permissive) · 4254dbfb6411b68f · report

Tasks

Node ClassificationNode Classification on Non-Homophilic (Heterophilic) GraphsNode Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Penn94 C&S 2-hop Accuracy 78.40 ± 3.12 #24 of 32 Archive leaderboard report
Node Classification Penn94 C&S 1-hop Accuracy 74.28 ± 1.19 #28 of 32 Archive leaderboard report
Node Classification genius C&S 2-hop Accuracy 84.94 ± 0.49 #17 of 26 Archive leaderboard report
Node Classification genius C&S 1-hop Accuracy 82.93 ± 0.15 #18 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Deezer-Europe C&S(1hop) 1:1 Accuracy 64.60±0.57 #19 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Deezer-Europe C&S(2hop) 1:1 Accuracy 64.52±0.62 #20 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 C&S 2-hop 1:1 Accuracy 78.40 ± 3.12 #20 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 C&S 1-hop 1:1 Accuracy 74.28 ± 1.19 #24 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius C&S 2-hop 1:1 Accuracy 84.94 ± 0.49 #19 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius C&S 1-hop 1:1 Accuracy 82.93 ± 0.15 #20 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers C&S 2-hop 1:1 Accuracy 65.02 ± 0.16 #11 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers C&S 1-hop 1:1 Accuracy 64.86 ± 0.27 #12 of 26 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT(norm.adj.)+label reuse+C&S Ext. data No #33 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT(norm.adj.)+label reuse+C&S Number of params 1441580 #33 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT(norm.adj.)+label reuse+C&S Test Accuracy 0.7395 ± 0.0012 #33 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT(norm.adj.)+label reuse+C&S Validation Accuracy 0.7519 ± 0.0008 #33 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT + C&S Ext. data No #35 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT + C&S Number of params 1567000 #35 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT + C&S Test Accuracy 0.7386 ± 0.0014 #35 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GAT + C&S Validation Accuracy 0.7484 ± 0.0007 #35 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + C&S_v2 Ext. data No #46 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + C&S_v2 Number of params 155824 #46 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + C&S_v2 Test Accuracy 0.7313 ± 0.0017 #46 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + C&S_v2 Validation Accuracy 0.7445 ± 0.0011 #46 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv MLP + C&S Ext. data No #47 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv MLP + C&S Number of params 175656 #47 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv MLP + C&S Test Accuracy 0.7312 ± 0.0012 #47 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv MLP + C&S Validation Accuracy 0.7391 ± 0.0015 #47 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + C&S Ext. data No #51 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + C&S Number of params 155824 #51 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + C&S Test Accuracy 0.7297 ± 0.0022 #51 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GCN_res + C&S Validation Accuracy 0.7423 ± 0.0014 #51 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv Linear + C&S Ext. data No #63 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv Linear + C&S Number of params 15400 #63 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv Linear + C&S Test Accuracy 0.7222 ± 0.0002 #63 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv Linear + C&S Validation Accuracy 0.7368 ± 0.0004 #63 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv Plain Linear + C&S Ext. data No #78 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv Plain Linear + C&S Number of params 5160 #78 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv Plain Linear + C&S Test Accuracy 0.7126 ± 0.0001 #78 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv Plain Linear + C&S Validation Accuracy 0.7300 ± 0.0001 #78 of 86 Archive leaderboard report
Node Property Prediction ogbn-products Spec-MLP-Wide + C&S Ext. data No #21 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Spec-MLP-Wide + C&S Number of params 406063 #21 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Spec-MLP-Wide + C&S Test Accuracy 0.8451 ± 0.0006 #21 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Spec-MLP-Wide + C&S Validation Accuracy 0.9132 ± 0.0010 #21 of 64 Archive leaderboard report
Node Property Prediction ogbn-products MLP + C&S Ext. data No #24 of 64 Archive leaderboard report
Node Property Prediction ogbn-products MLP + C&S Number of params 96247 #24 of 64 Archive leaderboard report
Node Property Prediction ogbn-products MLP + C&S Test Accuracy 0.8418 ± 0.0007 #24 of 64 Archive leaderboard report
Node Property Prediction ogbn-products MLP + C&S Validation Accuracy 0.9147 ± 0.0009 #24 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Linear + C&S Ext. data No #31 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Linear + C&S Number of params 10763 #31 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Linear + C&S Test Accuracy 0.8301 ± 0.0001 #31 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Linear + C&S Validation Accuracy 0.9134 ± 0.0001 #31 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Plain Linear + C&S Ext. data No #33 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Plain Linear + C&S Number of params 4747 #33 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Plain Linear + C&S Test Accuracy 0.8254 ± 0.0003 #33 of 64 Archive leaderboard report
Node Property Prediction ogbn-products Plain Linear + C&S Validation Accuracy 0.9103 ± 0.0001 #33 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GAT w/NS + C&S Ext. data No #42 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GAT w/NS + C&S Number of params 753622 #42 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GAT w/NS + C&S Test Accuracy 0.8092 ± 0.0037 #42 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GAT w/NS + C&S Validation Accuracy 0.9263 ± 0.0008 #42 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GraphSAGE w/NS + C&S Ext. data No #45 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GraphSAGE w/NS + C&S Number of params 207919 #45 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GraphSAGE w/NS + C&S Test Accuracy 0.8041 ± 0.0022 #45 of 64 Archive leaderboard report
Node Property Prediction ogbn-products GraphSAGE w/NS + C&S Validation Accuracy 0.9238 ± 0.0007 #45 of 64 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.

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