Papers › Finding Global Homophily in Graph Neural Networks When Meeting Heterophily

Finding Global Homophily in Graph Neural Networks When Meeting Heterophily

15 May 2022arXiv:2205.07308archive 2025-07-28

Xiang Li, Renyu Zhu, Yao Cheng, Caihua Shan, Siqiang Luo, Dongsheng Li, Weining Qian

We investigate graph neural networks on graphs with heterophily. Some existing methods amplify a node's neighborhood with multi-hop neighbors to include more nodes with homophily. However, it is a significant challenge to set personalized neighborhood sizes for different nodes. Further, for other homophilous nodes excluded in the neighborhood, they are ignored for information aggregation. To address these problems, we propose two models GloGNN and GloGNN++, which generate a node's embedding by aggregating information from global nodes in the graph. In each layer, both models learn a coefficient matrix to capture the correlations between nodes, based on which neighborhood aggregation is performed. The coefficient matrix allows signed values and is derived from an optimization problem that has a closed-form solution. We further accelerate neighborhood aggregation and derive a linear time complexity. We theoretically explain the models' effectiveness by proving that both the coefficient matrix and the generated node embedding matrix have the desired grouping effect. We conduct extensive experiments to compare our models against 11 other competitors on 15 benchmark datasets in a wide range of domains, scales and graph heterophilies. Experimental results show that our methods achieve superior performance and are also very efficient.

PaperPDFCodeMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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.

Syntology holds a reference implementation of GloGNN++, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='GloGNN++') (how to connect); the free check have('2205.07308') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

recklessronan/glognn officialmentioned in paperpytorchSyntology: not harvested 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

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

generated Assembly for GloGNN++ (graph method: GloGNN++), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. glognn_layer_forward entry · level 3 · ran · honoured contract · 66ff256a36606773bc9b68476355b843dffb8f128b937931c18bad6b73016cd8

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="2205.07308") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Node ClassificationNode Classification on Non-Homophilic (Heterophilic) Graphs

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Actor GloGNN++ Accuracy 37.7 ± 1.40 #18 of 62 Archive leaderboard report
Node Classification Actor GloGNN Accuracy 37.35 ± 1.30 #25 of 62 Archive leaderboard report
Node Classification Chameleon GloGNN++ Accuracy 71.21±1.84 #25 of 61 Archive leaderboard report
Node Classification Chameleon GloGNN Accuracy 69.78±2.42 #31 of 61 Archive leaderboard report
Node Classification Citeseer (48%/32%/20% fixed splits) GloGNN 1:1 Accuracy 77.41 ± 1.65 #4 of 26 Archive leaderboard report
Node Classification Citeseer (48%/32%/20% fixed splits) GloGNN++ 1:1 Accuracy 77.22 ± 1.78 #6 of 26 Archive leaderboard report
Node Classification Cora (48%/32%/20% fixed splits) GloGNN++ 1:1 Accuracy 88.33 ± 1.09 #3 of 26 Archive leaderboard report
Node Classification Cora (48%/32%/20% fixed splits) GloGNN 1:1 Accuracy 88.31 ± 1.13 #4 of 26 Archive leaderboard report
Node Classification Cornell GloGNN++ Accuracy 85.95±5.10 #14 of 60 Archive leaderboard report
Node Classification Cornell GloGNN Accuracy 83.51±4.26 #29 of 60 Archive leaderboard report
Node Classification Penn94 GloGNN++ Accuracy 85.74±0.42 #4 of 32 Archive leaderboard report
Node Classification Penn94 GloGNN Accuracy 85.57 ± 0.35 #5 of 32 Archive leaderboard report
Node Classification PubMed (48%/32%/20% fixed splits) GloGNN 1:1 Accuracy 89.62 ± 0.35 #8 of 26 Archive leaderboard report
Node Classification PubMed (48%/32%/20% fixed splits) GloGNN++ 1:1 Accuracy 89.24 ± 0.39 #13 of 26 Archive leaderboard report
Node Classification Squirrel GloGNN++ Accuracy 57.88±1.76– #28 of 59 Archive leaderboard report
Node Classification Squirrel GloGNN Accuracy 57.54±1.39 #30 of 59 Archive leaderboard report
Node Classification Texas GloGNN Accuracy 84.32±4.15 #36 of 62 Archive leaderboard report
Node Classification Texas GloGNN++ Accuracy 84.05±4.90 #38 of 62 Archive leaderboard report
Node Classification Wisconsin GloGNN++ Accuracy 88.04±3.22 #19 of 63 Archive leaderboard report
Node Classification Wisconsin GloGNN Accuracy 87.06±3.53 #31 of 63 Archive leaderboard report
Node Classification arXiv-year GloGNN++ Accuracy 54.79±0.25 #9 of 12 Archive leaderboard report
Node Classification genius GloGNN++ Accuracy 90.91 ± 0.13 #6 of 26 Archive leaderboard report
Node Classification genius GloGNN Accuracy 90.66 ± 0.11 #9 of 26 Archive leaderboard report
Node Classification genius GCNJK Accuracy 89.30 ± 0.19 #13 of 26 Archive leaderboard report
Node Classification genius MLP Accuracy 86.68 ± 0.09 #15 of 26 Archive leaderboard report
Node Classification pokec GloGNN++ Accuracy 83.05±0.07 #4 of 7 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon (48%/32%/20% fixed splits) GloGNN++ 1:1 Accuracy 71.21 ± 1.84  #8 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon (48%/32%/20% fixed splits) GloGNN 1:1 Accuracy 69.78 ± 2.42  #12 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (48%/32%/20% fixed splits) GloGNN++ 1:1 Accuracy 85.95 ± 5.10  #3 of 27 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (48%/32%/20% fixed splits) GloGNN 1:1 Accuracy 83.51 ± 4.26 #14 of 27 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Film(48%/32%/20% fixed splits) GloGNN++ 1:1 Accuracy 37.70 ± 1.40  #5 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Film(48%/32%/20% fixed splits) GloGNN 1:1 Accuracy 37.35 ± 1.30 #8 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 GloGNN++ 1:1 Accuracy 85.74 ± 0.42 #3 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 GloGNN 1:1 Accuracy 85.57 ± 0.35 #4 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Squirrel (48%/32%/20% fixed splits) GloGNN++ 1:1 Accuracy 57.88 ± 1.76  #11 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Squirrel (48%/32%/20% fixed splits) GloGNN 1:1 Accuracy 57.54 ± 1.39  #12 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) GloGNN 1:1 Accuracy 84.32 ± 4.15  #12 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) GloGNN++ 1:1 Accuracy 84.05 ± 4.90 #14 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin (48%/32%/20% fixed splits) GloGNN++ 1:1 Accuracy  88.04 ± 3.22  #8 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin (48%/32%/20% fixed splits) GloGNN 1:1 Accuracy 87.06 ± 3.53  #13 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius GloGNN++ 1:1 Accuracy 90.91 ± 0.13 #8 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs genius GloGNN 1:1 Accuracy 90.66 ± 0.11 #11 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers GloGNN++ 1:1 Accuracy 66.34 ± 0.29 #3 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs twitch-gamers GloGNN 1:1 Accuracy 66.19 ± 0.29 #5 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