Papers › Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

27 Oct 2021NeurIPS 2021 12arXiv:2110.14446archive 2025-07-28

Derek Lim, Felix Hohne, Xiuyu Li, Sijia Linda Huang, Vaishnavi Gupta, Omkar Bhalerao, Ser-Nam Lim

Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other. Recently, new Graph Neural Networks (GNNs) have been developed that move beyond the homophily regime; however, their evaluation has often been conducted on small graphs with limited application domains. We collect and introduce diverse non-homophilous datasets from a variety of application areas that have up to 384x more nodes and 1398x more edges than prior datasets. We further show that existing scalable graph learning and graph minibatching techniques lead to performance degradation on these non-homophilous datasets, thus highlighting the need for further work on scalable non-homophilous methods. To address these concerns, we introduce LINKX -- a strong simple method that admits straightforward minibatch training and inference. Extensive experimental results with representative simple methods and GNNs across our proposed datasets show that LINKX achieves state-of-the-art performance for learning on non-homophilous graphs. Our codes and data are available at https://github.com/CUAI/Non-Homophily-Large-Scale.

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 (cuai/non-homophily-large-scale) is linked to this paper; the 21 samples below come from 3 community repositories. Syntology harvested code from cuai/non-homophily-large-scale for another paper.

cuai/non-homophily-large-scale: Syntology's graph links these samples to Glance for Context: Learning When to Leverage LLMs for Node-Aware GNN-LLM Fusion (arXiv:2510.10849; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method.

Syntology 21 code samples harvested from 3 repositories linked to this paper: 15 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 21 samples from 3 repositories, 15 ran (10 with no instrument failure; 5 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 2 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.

cuai/non-homophily-large-scale officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Glance for Context: Learning When to Leverage LLMs for Node-Aware GNN-LLM Fusion (arXiv:2510.10849; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
CUAI/Non-Homophily-Benchmarks mentioned on GitHubpytorchMITSyntology: 13 samples, 9 ran (5 instrument-failed) · 4 unverified report
ivam-he/chebnetii mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
kkhuang81/AdaptKry mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Optimizing Polynomial Graph Filters: A Novel Adaptive Krylov Subspace Approach (arXiv:2403.07954; that paper's own run record: 5 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; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
kkhuang81/UniFilter mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 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

21 samples harvested: 15 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
4ran; the contract check could not run
9ran
6unverified

Licence: 11 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 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 3 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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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/Non-Homophily-Benchmarks community (archive-listed) 13 samples, 9 ran (5 instrument-failed) · 4 unverified
compat_matrix homophily.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 606e13d2f58cd737 · report fixture: signature A:csr_matrix/2/int, labels:ndarray/1/int · returned ndarray · level recorded 2026-09-25
edge_homophily in 6 papers homophily.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 07270c9ae73d7519 · report fixture: signature A:csr_matrix/2/int, labels:ndarray/1/int, ignore_negative:bool/0/bool · returned float64 · level recorded 2026-09-25
general_outcome_correlation correct_smooth.py ran MIT (permissive) · 10001c8b8b43dfbc · report fixture: signature adj:Tensor/2/float, y:Tensor/2/float, alpha:float/0/float, num_propagations:int/0/int, post_step:callable/0/?, alpha_term:bool/0/bool, num_hops:int/0/int, device:str/0/str, display:bool/0/bool · returned Tensor · level recorded 2026-09-24
node_homophily in 6 papers homophily.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 42ea8a2b9adf3c0e · report fixture: signature A:csr_matrix/2/float, labels:ndarray/1/int · returned Tensor · level recorded 2026-09-25
pre_residual_correlation correct_smooth.py ran MIT (permissive) · cce358b08f0d5b50 · report fixture: signature labels:Tensor/2/float, model_out:Tensor/2/float, label_idx:Tensor/1/int · returned Tensor · level recorded 2026-09-24
rand_train_test_idx in 18 papers data_utils.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 13234652741e2264 · report fixture: signature label:Tensor/1/int, train_prop:float/0/float, valid_prop:float/0/float, ignore_negative:bool/0/bool · returned tuple · level recorded 2026-09-25
test in 377 papers gcn-ogbn-proteins.py ran MIT (permissive) · 38233058d8c3af1b · report fixture: signature model:callable/0/?, data:Data/0/?, split_idx:dict/0/?, evaluator:Evaluator/0/? · returned tuple · level recorded 2026-09-24
to_planetoid in 9 papers data_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 7e85cbb79f6726cb · report fixture: signature dataset:MockNCDataset/0/? · returned tuple · level recorded 2026-09-24
train in 522 papers gcn-ogbn-proteins.py ran MIT (permissive) · fcac6adae654a353 · report fixture: signature model:callable/0/?, data:Data/0/?, train_idx:Tensor/1/int, optimizer:Adam/0/? · returned float · level recorded 2026-09-24
even_quantile_labels in 21 papers data_utils.py unverified MIT (permissive) here; the stored copy is pointer only · 919cb6dbf2c173bb · report
load_fb100 in 12 papers load_data.py unverified MIT (permissive) · ab0d9da60756efc3 · report
load_twitch in 11 papers load_data.py unverified MIT (permissive) here; the stored copy is pointer only · 563a5ce4dce55a17 · report
pre_outcome_correlation correct_smooth.py unverified MIT (permissive) · 46e8aa0d0cec5dee · report
ivam-he/chebnetii community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
MLP in 375 papers non-homophilous/models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 65a58883cfe40082 · report fixture: returned MLP · level recorded 2026-09-22
cheby in 5 papers non-homophilous/models.py ran · honoured contract no licence file found · pointer only · d7653b0093307e2d · report fixture: signature i:int/0/int, x:float/0/float · returned float · level recorded 2026-09-22
ChebNetII_V non-homophilous/models.py unverified no licence file found · pointer only · c57ba20da37784b4 · report
ChebnetII_prop non-homophilous/models.py unverified no licence file found · pointer only · bb80980e3fb3c30c · report
kkhuang81/UniFilter community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Combination non-homo/models.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 91c76597ab622382 · report fixture: returned Combination · level recorded 2026-09-22
Dense in 22 papers non-homo/models.py ran · metamorphic tier: deterministic MIT (permissive) · 382d674885c1d7a8 · report fixture: returned Dense · level recorded 2026-09-22
GFK non-homo/models.py ran · metamorphic tier: deterministic MIT (permissive) · aefb7362513b6d9c · report fixture: returned GFK · level recorded 2026-09-22
MLP in 375 papers non-homo/models.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 1ec411235e21d6aa · report fixture: returned MLP · level recorded 2026-09-22

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

  1. GFK entry · level 1 · ran · aefb7362513b6d9c
  2. Combination model · level 1 · ran · 91c76597ab622382
  3. MLP helper · level 1 · ran · 1ec411235e21d6aa
  4. Dense helper · level 1 · ran · 382d674885c1d7a8

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="2110.14446") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Graph LearningNode ClassificationNode Classification on Non-Homophilic (Heterophilic) Graphs

Datasets

Introduced by this paper, per the archive.

Penn94geniustwitch-gamers

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Actor LINKX Accuracy 36.10 ± 1.55 #41 of 62 Archive leaderboard report
Node Classification Chameleon LINKX Accuracy 68.42 ± 1.38 #39 of 61 Archive leaderboard report
Node Classification Citeseer (48%/32%/20% fixed splits) LINKX 1:1 Accuracy 73.19 ± 0.99 #25 of 26 Archive leaderboard report
Node Classification Cora (48%/32%/20% fixed splits) LINKX 1:1 Accuracy 84.64 ± 1.13 #24 of 26 Archive leaderboard report
Node Classification Cornell LINKX Accuracy 77.84 ± 5.81 #45 of 60 Archive leaderboard report
Node Classification Penn94 LINKX Accuracy 84.71 ± 0.52 #11 of 32 Archive leaderboard report
Node Classification PubMed (48%/32%/20% fixed splits) LINKX 1:1 Accuracy 87.86 ± 0.77 #23 of 26 Archive leaderboard report
Node Classification Squirrel LINKX Accuracy 61.81 ± 1.80 #24 of 59 Archive leaderboard report
Node Classification Texas LINKX Accuracy 74.60 ± 8.37 #54 of 62 Archive leaderboard report
Node Classification Wisconsin LINKX Accuracy 75.49 ± 5.72 #56 of 63 Archive leaderboard report
Node Classification arXiv-year LINKX Accuracy 56.00±1.34 #7 of 12 Archive leaderboard report
Node Classification genius LINKX Accuracy 90.77 ± 0.27 #8 of 26 Archive leaderboard report
Node Classification pokec LINKX Accuracy 82.04±0.07 #6 of 7 Archive leaderboard report
Node Classification twitch-gamers LINKX Accuracy 66.06±0.19 #2 of 2 Archive leaderboard report
Node Classification wiki LINKX ACCURACY 59.80±0.41 #2 of 2 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon (48%/32%/20% fixed splits) LINKX 1:1 Accuracy 68.42 ± 1.38  #16 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (48%/32%/20% fixed splits) LINKX 1:1 Accuracy  77.84 ± 5.81  #22 of 27 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Film(48%/32%/20% fixed splits) LINKX 1:1 Accuracy 36.10 ± 1.55  #17 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 LINKX 1:1 Accuracy 84.71 ± 0.52 #7 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 GCNJK 1:1 Accuracy 81.63 ± 0.54 #13 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 LINK 1:1 Accuracy 80.79 ± 0.49 #17 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 GATJK 1:1 Accuracy 80.69 ± 0.36 #18 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 L Prop 2-hop 1:1 Accuracy 74.13 ± 0.46 #25 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 L Prop 1-hop 1:1 Accuracy 63.21 ± 0.39 #28 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Squirrel (48%/32%/20% fixed splits) LINKX 1:1 Accuracy 61.81 ± 1.80 #9 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) LINKX 1:1 Accuracy 74.60 ± 8.37  #23 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin (48%/32%/20% fixed splits) LINKX 1:1 Accuracy 75.49 ± 5.72 #23 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius LINKX 1:1 Accuracy 90.77 ± 0.27 #10 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius GCNJK 1:1 Accuracy 89.30 ± 0.19 #15 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius MLP 1:1 Accuracy 86.68 ± 0.09 #17 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius LINK 1:1 Accuracy 73.56 ± 0.14 #23 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius L Prop 2-hop 1:1 Accuracy 67.04 ± 0.20 #24 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius L Prop 1-hop 1:1 Accuracy 66.02 ± 0.16 #25 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius GATJK 1:1 Accuracy 56.70 ± 2.07 #26 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers LINKX 1:1 Accuracy 66.06 ± 0.19 #6 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers LINK 1:1 Accuracy 64.85 ± 0.21 #13 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers L Prop 2-hop 1:1 Accuracy 63.88 ± 0.24 #15 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers GCNJK 1:1 Accuracy 63.45 ± 0.22 #17 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers L Prop 1-hop 1:1 Accuracy 62.77 ± 0.24 #19 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers MLP 1:1 Accuracy 60.92 ± 0.07 #23 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers GATJK 1:1 Accuracy 59.98 ± 2.87 #24 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