Papers › Geom-GCN: Geometric Graph Convolutional Networks

Geom-GCN: Geometric Graph Convolutional Networks

13 Feb 2020ICLR 2020 1arXiv:2002.05287archive 2025-07-28

Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, Bo Yang

Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent graph-structured data: losing the structural information of nodes in neighborhoods and lacking the ability to capture long-range dependencies in disassortative graphs. Few studies have noticed the weaknesses from different perspectives. From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses. The behind basic idea is the aggregation on a graph can benefit from a continuous space underlying the graph. The proposed aggregation scheme is permutation-invariant and consists of three modules, node embedding, structural neighborhood, and bi-level aggregation. We also present an implementation of the scheme in graph convolutional networks, termed Geom-GCN (Geometric Graph Convolutional Networks), to perform transductive learning on graphs. Experimental results show the proposed Geom-GCN achieved state-of-the-art performance on a wide range of open datasets of graphs. Code is available at https://github.com/graphdml-uiuc-jlu/geom-gcn.

PaperPDFConference PDFCodeCode 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

No sample from the archive's official repository (graphdml-uiuc-jlu/geom-gcn) is linked to this paper; the 7 samples below come from 2 community repositories. Syntology harvested code from graphdml-uiuc-jlu/geom-gcn for another paper.

graphdml-uiuc-jlu/geom-gcn: Syntology's graph links these samples to Simple and Asymmetric Graph Contrastive Learning without Augmentations (arXiv:2310.18884; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 7 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 7 samples from 2 repositories, 7 ran (3 with no instrument failure; 4 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 7 samples that ran have no recorded date.

graphdml-uiuc-jlu/geom-gcn officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Simple and Asymmetric Graph Contrastive Learning without Augmentations (arXiv:2310.18884; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
KAIDI3270/Geom_GCN_pytorch_implementation mentioned on GitHubpytorchSyntology: not harvested report
alexfanjn/geomgcn_pyg mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (2 instrument-failed) · 0 unverified report
bingzhewei/geom-gcn mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 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.

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

7 samples harvested: 7 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 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.

1ran · honoured contract
4ran · our draft was wrong
2ran

Licence: 7 of the 7 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. 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.

alexfanjn/geomgcn_pyg community (archive-listed) 4 samples, 4 ran (2 instrument-failed) · 0 unverified
GeomGCN model.py ran no licence file found · pointer only · fdae60f85c7b410e · report fixture: returned GeomGCN · level recorded 2026-09-22
GeomGCN_layer model.py ran no licence file found · pointer only · 2ef6fd9f93ca6ebf · report fixture: returned GeomGCN_layer · level recorded 2026-09-22
edge_index_to_sparse_tensor_adj model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c187bf050bb2c556 · report fixture: signature edge_index:Tensor/2/int, num_nodes:int/0/int · returned Tensor · level recorded 2026-09-22
gcn_norm in 6 papers model.py ran · our draft was wrong no licence file found · pointer only · 0626d35807929da7 · report fixture: signature edge_index:Tensor/2/int, num_nodes:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-22
bingzhewei/geom-gcn community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
load_data in 700 papers utils.py ran · our draft was wrong no licence file found · pointer only · 32302e598b1afb70 · report fixture: signature dataset_str:str/0/str · returned tuple · level recorded, date not recorded
parse_index_file in 54 papers utils.py ran · honoured contract no licence file found · pointer only · dfd091f34611a47a · report fixture: signature filename:str/0/str · returned list · level recorded, date not recorded
sample_mask in 39 papers
census: 4 implementations from 5 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
utils.py ran · our draft was wrong no licence file found · pointer only · 61cb7d8c95b55c0c · report fixture: signature idx:ndarray/1/int, l:int/0/int · returned ndarray · level recorded, date not recorded

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Geom-GCN (graph method: Geom-GCN). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. GeomGCN entry · level 1 · ran · fdae60f85c7b410e
  2. GeomGCN_layer model · level 1 · ran · 2ef6fd9f93ca6ebf
  3. gcn_norm helper · level 1 · ran · our draft was wrong · 0626d35807929da7
  4. edge_index_to_sparse_tensor_adj helper · level 1 · ran · our draft was wrong · c187bf050bb2c556

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="2002.05287") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Node ClassificationNode Classification on Non-Homophilic (Heterophilic) GraphsRepresentation LearningTransductive Learning

Datasets

Introduced by this paper, per the archive.

Chameleon (48%/32%/20% fixed splits)Citeseer (48%/32%/20% fixed splits)Cora (48%/32%/20% fixed splits)Cornell (48%/32%/20% fixed splits)Film(48%/32%/20% fixed splits)PubMed (48%/32%/20% fixed splits)Squirrel (48%/32%/20% fixed splits)Texas (48%/32%/20% fixed splits)Wisconsin (48%/32%/20% fixed splits)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Actor Geom-GCN-P Accuracy 31.63 #56 of 62 Archive leaderboard report
Node Classification Actor Geom-GCN-S Accuracy 30.3 #58 of 62 Archive leaderboard report
Node Classification Actor Geom-GCN-I Accuracy 29.09 #61 of 62 Archive leaderboard report
Node Classification Chameleon Geom-GCN-P Accuracy 60.9 #50 of 61 Archive leaderboard report
Node Classification Chameleon Geom-GCN-I Accuracy 60.31 #52 of 61 Archive leaderboard report
Node Classification Chameleon Geom-GCN-S Accuracy 59.96 #53 of 61 Archive leaderboard report
Node Classification Chameleon (60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 60.9 #29 of 38 Archive leaderboard report
Node Classification CiteSeer (60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 77.99 #26 of 33 Archive leaderboard report
Node Classification Citeseer (48%/32%/20% fixed splits) Geom-GCN 1:1 Accuracy 78.02 ± 1.15 #1 of 26 Archive leaderboard report
Node Classification Cora (48%/32%/20% fixed splits) Geom-GCN 1:1 Accuracy 85.35 ± 1.57 #23 of 26 Archive leaderboard report
Node Classification Cora (60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 85.27 #27 of 33 Archive leaderboard report
Node Classification Cornell Geom-GCN-P Accuracy 60.81 #53 of 60 Archive leaderboard report
Node Classification Cornell Geom-GCN-I Accuracy 56.76 #56 of 60 Archive leaderboard report
Node Classification Cornell Geom-GCN-S Accuracy 55.68 #57 of 60 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 60.81 #35 of 36 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 31.63 #34 of 37 Archive leaderboard report
Node Classification PubMed (48%/32%/20% fixed splits) Geom-GCN 1:1 Accuracy 89.95 ± 0.47 #2 of 26 Archive leaderboard report
Node Classification PubMed (60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 90.05 #17 of 37 Archive leaderboard report
Node Classification Squirrel Geom-GCN-P Accuracy 38.14 #52 of 59 Archive leaderboard report
Node Classification Squirrel Geom-GCN-S Accuracy 36.24 #54 of 59 Archive leaderboard report
Node Classification Squirrel Geom-GCN-I Accuracy 33.32 #56 of 59 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 38.14 #33 of 37 Archive leaderboard report
Node Classification Texas Geom-GCN-P Accuracy 67.57 #56 of 62 Archive leaderboard report
Node Classification Texas Geom-GCN-S Accuracy 59.73 #60 of 62 Archive leaderboard report
Node Classification Texas Geom-GCN-I Accuracy 57.58 #61 of 62 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 67.57 #36 of 36 Archive leaderboard report
Node Classification Wisconsin Geom-GCN-P Accuracy 64.12 #58 of 63 Archive leaderboard report
Node Classification Wisconsin Geom-GCN-I Accuracy 58.24 #60 of 63 Archive leaderboard report
Node Classification Wisconsin Geom-GCN-S Accuracy 56.67 #62 of 63 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 64.12 #34 of 35 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon (48%/32%/20% fixed splits) Geom-GCN 1:1 Accuracy 60.00 ± 2.81 #26 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon(60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 60.9 #24 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (48%/32%/20% fixed splits) Geom-GCN 1:1 Accuracy 60.54 ± 3.67 #25 of 27 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 60.81 #32 of 33 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Film(48%/32%/20% fixed splits) Geom-GCN 1:1 Accuracy 31.59 ± 1.15 #25 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Squirrel (48%/32%/20% fixed splits) Geom-GCN 1:1 Accuracy 38.15 ± 0.92 #26 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) Geom-GCN 1:1 Accuracy 66.76 ± 2.72 #24 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas(60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 67.57 #32 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin (48%/32%/20% fixed splits) Geom-GCN 1:1 Accuracy 64.51 ± 3.66 #24 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin(60%/20%/20% random splits) Geom-GCN* 1:1 Accuracy 64.12 #31 of 32 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