Papers › Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs...

Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns

11 Jun 2021arXiv:2106.06586archive 2025-07-28

Susheel Suresh, Vinith Budde, Jennifer Neville, Pan Li, Jianzhu Ma

Graph neural networks (GNNs) have achieved tremendous success on multiple graph-based learning tasks by fusing network structure and node features. Modern GNN models are built upon iterative aggregation of neighbor's/proximity features by message passing. Its prediction performance has been shown to be strongly bounded by assortative mixing in the graph, a key property wherein nodes with similar attributes mix/connect with each other. We observe that real world networks exhibit heterogeneous or diverse mixing patterns and the conventional global measurement of assortativity, such as global assortativity coefficient, may not be a representative statistic in quantifying this mixing. We adopt a generalized concept, node-level assortativity, one that is based at the node level to better represent the diverse patterns and accurately quantify the learnability of GNNs. We find that the prediction performance of a wide range of GNN models is highly correlated with the node level assortativity. To break this limit, in this work, we focus on transforming the input graph into a computation graph which contains both proximity and structural information as distinct type of edges. The resulted multi-relational graph has an enhanced level of assortativity and, more importantly, preserves rich information from the original graph. We then propose to run GNNs on this computation graph and show that adaptively choosing between structure and proximity leads to improved performance under diverse mixing. Empirically, we show the benefits of adopting our transformation framework for semi-supervised node classification task on a variety of real world graph learning benchmarks.

PaperPDFCodeCode 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 12 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 6 ran (5 with no instrument failure; 1 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

susheels/gnns-and-local-assortativity officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 6 ran (1 instrument-failed) · 6 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

12 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 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 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 · our draft was wrong
5ran
6unverified

Licence: 0 of the 12 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 susheels/gnns-and-local-assortativity. “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.

susheels/gnns-and-local-assortativity official repository 12 samples, 6 ran (1 instrument-failed) · 6 unverified
check_rm datasets/bgp.py ran MIT (permissive) · f6a38e82cb7bacde · report fixture: signature neighbors_set:set/0/?, unlabeled_nodes:set/0/? · returned bool · level recorded 2026-09-25
chooseNeighbor struc_sim/algorithms.py ran MIT (permissive) · a031777e4ebeff8a · report fixture: signature v:int/0/int, graphs:dict/0/?, alias_method_j:dict/0/?, alias_method_q:dict/0/?, layer:int/0/int · returned int · level recorded 2026-09-25
convert_ndarray datasets/bgp.py ran MIT (permissive) · 7984390414b770ba · report fixture: signature x:dict/0/? · returned ndarray · level recorded 2026-09-26
filter_rels exp.py ran · our draft was wrong MIT (permissive) · 5e3663ee66aeb1d8 · report fixture: signature data:MockData/0/?, r:int/0/int · returned MockData · level recorded 2026-09-22
get_degrees datasets/airports.py ran MIT (permissive) · a093c2a5cfaf259d · report fixture: signature G:Graph/0/? · returned ndarray · level recorded 2026-09-26
rm_useless datasets/bgp.py ran MIT (permissive) · 4102c2d70e0e526f · report fixture: signature G:Graph/0/?, feats:ndarray/2/float, class_map:ndarray/1/int, unlabeled_nodes:list/1/int, num_layers:int/0/int · returned tuple · level recorded 2026-09-25
build_multigraph_from_layers build_multigraph.py unverified MIT (permissive) · 5d28fa208f6b62a9 · report
exec_ramdom_walks_for_chunck struc_sim/algorithms.py unverified MIT (permissive) · e2522114d54ff7a8 · report
exec_random_walk struc_sim/algorithms.py unverified MIT (permissive) · 686c85e304c59420 · report
getCompactDegreeLists struc_sim/algorithms_distances.py unverified MIT (permissive) · be0549eb08da272a · report
getCompactDegreeListsVertices struc_sim/algorithms_distances.py unverified MIT (permissive) · 0dfca563e6da5c5a · report
getDegreeListsVertices struc_sim/algorithms_distances.py unverified MIT (permissive) · 4ae621b1fc59fd88 · report

Tasks

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

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Actor WRGAT Accuracy 36.53 ± 0.77 #34 of 62 Archive leaderboard report
Node Classification Chameleon WRGAT Accuracy 65.24 ± 0.87 #44 of 61 Archive leaderboard report
Node Classification Citeseer (48%/32%/20% fixed splits) WRGAT 1:1 Accuracy 76.81 ± 1.89 #15 of 26 Archive leaderboard report
Node Classification Cora (48%/32%/20% fixed splits) WRGAT 1:1 Accuracy 88.20 ± 2.26 #6 of 26 Archive leaderboard report
Node Classification Cornell WRGAT Accuracy 81.62 ± 3.90 #38 of 60 Archive leaderboard report
Node Classification Penn94 WRGAT Accuracy 74.32 ± 0.53 #27 of 32 Archive leaderboard report
Node Classification PubMed (48%/32%/20% fixed splits) WRGAT 1:1 Accuracy 88.52 ± 0.92 #18 of 26 Archive leaderboard report
Node Classification Squirrel WRGAT Accuracy 48.85 ± 0.78 #43 of 59 Archive leaderboard report
Node Classification Texas WRGAT Accuracy 83.62 ± 5.50 #41 of 62 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon (48%/32%/20% fixed splits) WRGAT 1:1 Accuracy 65.24 ± 0.87  #20 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (48%/32%/20% fixed splits) WRGAT 1:1 Accuracy 81.62 ±3.90  #18 of 27 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Film(48%/32%/20% fixed splits) WRGAT 1:1 Accuracy 36.53 ± 0.77  #13 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Penn94 WRGAT 1:1 Accuracy 74.32 ± 0.53 #23 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Squirrel (48%/32%/20% fixed splits) WRGAT 1:1 Accuracy 48.85 ± 0.78 #20 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) WRGAT 1:1 Accuracy 83.62 ± 5.50  #15 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin (48%/32%/20% fixed splits) WRGAT 1:1 Accuracy 86.98 ± 3.78  #14 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