Papers › Non-Local Graph Neural Networks

Non-Local Graph Neural Networks

29 May 2020arXiv:2005.14612archive 2025-07-28

Meng Liu, Zhengyang Wang, Shuiwang Ji

Modern graph neural networks (GNNs) learn node embeddings through multilayer local aggregation and achieve great success in applications on assortative graphs. However, tasks on disassortative graphs usually require non-local aggregation. In addition, we find that local aggregation is even harmful for some disassortative graphs. In this work, we propose a simple yet effective non-local aggregation framework with an efficient attention-guided sorting for GNNs. Based on it, we develop various non-local GNNs. We perform thorough experiments to analyze disassortative graph datasets and evaluate our non-local GNNs. Experimental results demonstrate that our non-local GNNs significantly outperform previous state-of-the-art methods on seven benchmark datasets of disassortative graphs, in terms of both model performance and efficiency.

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 3 code samples harvested from 1 repository linked to this paper: 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) · 0 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 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.

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

divelab/Non-Local-GNN officialpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified 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

3 samples harvested: 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) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

3ran · our draft was wrong

Licence: 3 of the 3 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 divelab/Non-Local-GNN. “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.

divelab/Non-Local-GNN official repository 3 samples, 3 ran (3 instrument-failed) · 0 unverified
index_to_mask in 25 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
NLGNN/src/train_eval.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · da80a2b9fd449bd2 · report fixture: signature index:Tensor/1/int, size:int/0/int · returned Tensor · level recorded 2026-09-22
random_disassortative_splits NLGNN/src/train_eval.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · ca063eb1dc48ac9f · report fixture: signature data:MockData/0/?, num_classes:int/0/int · returned MockData · level recorded 2026-09-22
random_planetoid_splits in 9 papers NLGNN/src/train_eval.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 12f00e9b50fb314f · report fixture: signature data:Data/0/?, num_classes:int/0/int, lcc_mask:NoneType/0/? · returned Data · level recorded 2026-09-22

Tasks

Node ClassificationNode Classification on Non-Homophilic (Heterophilic) Graphs

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Actor NLMLP Accuracy 37.9 ± 1.3 #13 of 62 Archive leaderboard report
Node Classification Actor NLGCN Accuracy 31.6 ± 1.0 #57 of 62 Archive leaderboard report
Node Classification Actor NLGAT Accuracy 29.5 ± 1.3 #59 of 62 Archive leaderboard report
Node Classification Chameleon NLGCN Accuracy 70.1 ± 2.9 #29 of 61 Archive leaderboard report
Node Classification Chameleon NLGAT Accuracy 65.7 ± 1.4 #43 of 61 Archive leaderboard report
Node Classification Chameleon NLMLP Accuracy 50.7 ± 2.2 #58 of 61 Archive leaderboard report
Node Classification Citeseer (48%/32%/20% fixed splits) NLGAT 1:1 Accuracy 76.2 ± 1.6 #21 of 26 Archive leaderboard report
Node Classification Citeseer (48%/32%/20% fixed splits) NLGCN 1:1 Accuracy 75.2 ± 1.4 #22 of 26 Archive leaderboard report
Node Classification Citeseer (48%/32%/20% fixed splits) NLMLP 1:1 Accuracy 73.4 ± 1.9 #24 of 26 Archive leaderboard report
Node Classification Cora (48%/32%/20% fixed splits) NLGAT 1:1 Accuracy 88.5 ± 1.8 #1 of 26 Archive leaderboard report
Node Classification Cora (48%/32%/20% fixed splits) NLGCN 1:1 Accuracy 88.1 ± 1.0 #9 of 26 Archive leaderboard report
Node Classification Cora (48%/32%/20% fixed splits) NLMLP 1:1 Accuracy 76.9 ± 1.8 #25 of 26 Archive leaderboard report
Node Classification Cornell NLMLP Accuracy 84.9 ± 5.7 #25 of 60 Archive leaderboard report
Node Classification Cornell NLGCN Accuracy 57.6 ± 5.5 #55 of 60 Archive leaderboard report
Node Classification Cornell NLGAT Accuracy 54.7 ± 7.6 #58 of 60 Archive leaderboard report
Node Classification PubMed (48%/32%/20% fixed splits) NLGCN 1:1 Accuracy 89.0 ± 0.5 #17 of 26 Archive leaderboard report
Node Classification PubMed (48%/32%/20% fixed splits) NLMLP 1:1 Accuracy 88.2 ± 0.5 #20 of 26 Archive leaderboard report
Node Classification PubMed (48%/32%/20% fixed splits) NLGAT 1:1 Accuracy 88.2 ± 0.3 #21 of 26 Archive leaderboard report
Node Classification Squirrel NLGCN Accuracy 59.0 ± 1.2 #27 of 59 Archive leaderboard report
Node Classification Squirrel NLGAT Accuracy 56.8 ± 2.5 #32 of 59 Archive leaderboard report
Node Classification Squirrel NLMLP Accuracy 33.7 ± 1.5 #55 of 59 Archive leaderboard report
Node Classification Texas NLMLP Accuracy 85.4 ± 3.8 #29 of 62 Archive leaderboard report
Node Classification Texas NLGCN Accuracy 65.5 ± 6.6 #57 of 62 Archive leaderboard report
Node Classification Texas NLGAT Accuracy 62.6 ± 7.1 #59 of 62 Archive leaderboard report
Node Classification Wisconsin NLMLP Accuracy 87.3 ± 4.3 #30 of 63 Archive leaderboard report
Node Classification Wisconsin NLGCN Accuracy 60.2 ± 5.3 #59 of 63 Archive leaderboard report
Node Classification Wisconsin NLGAT Accuracy 56.9 ± 7.3 #61 of 63 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon (48%/32%/20% fixed splits) NLGCN 1:1 Accuracy 70.1 ± 2.9 #11 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon (48%/32%/20% fixed splits) NLGAT 1:1 Accuracy 65.7 ± 1.4 #19 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon (48%/32%/20% fixed splits) NLMLP 1:1 Accuracy 50.7 ± 2.2 #28 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (48%/32%/20% fixed splits) NLMLP 1:1 Accuracy 84.9 ± 5.7 #12 of 27 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (48%/32%/20% fixed splits) NLGCN 1:1 Accuracy 57.6 ± 5.5 #26 of 27 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (48%/32%/20% fixed splits) NLGAT 1:1 Accuracy 54.7 ± 7.6 #27 of 27 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Film(48%/32%/20% fixed splits) NLMLP 1:1 Accuracy 37.9 ± 1.3 #1 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Film(48%/32%/20% fixed splits) NLGCN 1:1 Accuracy 31.6 ± 1.0 #24 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Film(48%/32%/20% fixed splits) NLGAT 1:1 Accuracy 29.5 ± 1.3 #26 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Squirrel (48%/32%/20% fixed splits) NLGCN 1:1 Accuracy 59.0 ± 1.2 #10 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Squirrel (48%/32%/20% fixed splits) NLGAT 1:1 Accuracy 56.8 ± 2.5 #13 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Squirrel (48%/32%/20% fixed splits) NLMLP 1:1 Accuracy 33.7 ± 1.5 #28 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) NLMLP 1:1 Accuracy 85.4 ± 3.8 #9 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) NLGCN 1:1 Accuracy 65.5 ± 6.6 #25 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) NLGAT 1:1 Accuracy 62.6 ± 7.1 #26 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin (48%/32%/20% fixed splits) NLMLP 1:1 Accuracy 87.3 ± 4.3  #12 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin (48%/32%/20% fixed splits) NLGCN 1:1 Accuracy 60.2 ± 5.3  #25 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin (48%/32%/20% fixed splits) NLGAT 1:1 Accuracy 56.9 ± 7.3 #26 of 26 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