Papers › Half-Hop: A graph upsampling approach for slowing down message passing

Half-Hop: A graph upsampling approach for slowing down message passing

17 Aug 2023arXiv:2308.09198archive 2025-07-28

Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor, Chi-Heng Lin, Lakshmi Sathidevi, Ran Liu, Michal Valko, Petar Veličković, Eva L. Dyer

Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail when neighboring nodes belong to different classes. In this work, we introduce a simple yet general framework for improving learning in message passing neural networks. Our approach essentially upsamples edges in the original graph by adding "slow nodes" at each edge that can mediate communication between a source and a target node. Our method only modifies the input graph, making it plug-and-play and easy to use with existing models. To understand the benefits of slowing down message passing, we provide theoretical and empirical analyses. We report results on several supervised and self-supervised benchmarks, and show improvements across the board, notably in heterophilic conditions where adjacent nodes are more likely to have different labels. Finally, we show how our approach can be used to generate augmentations for self-supervised learning, where slow nodes are randomly introduced into different edges in the graph to generate multi-scale views with variable path lengths.

PaperPDFCodeCode 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

Syntology 1 code sample harvested from 1 repository linked to this paper: 0 ran · 1 unverified.

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

nerdslab/halfhop officialmentioned in paperpytorchSyntology: 1 sample, 0 ran · 1 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

1 sample harvested: 0 ran · 1 unverified. 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.

1unverified

Licence: 0 of the 1 sample 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 nerdslab/halfhop. “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. “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.

nerdslab/halfhop official repository 1 sample, 0 ran · 1 unverified
HalfHop halfhop.py unverified Apache-2.0 (permissive) · 0ca29413fb690b70 · report

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 Half-Hop (graph method: Half-Hop). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. HalfHop entry · level 0 · unverified · 0ca29413fb690b70

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="2308.09198") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Node ClassificationSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification AMZ Comp HH-GCN Accuracy 90.92% #1 of 7 Archive leaderboard report
Node Classification AMZ Comp GCN Accuracy 90.22% #2 of 7 Archive leaderboard report
Node Classification AMZ Comp HH-GraphSAGE Accuracy 86.6% #4 of 7 Archive leaderboard report
Node Classification AMZ Comp GraphSAGE Accuracy 84.79% #6 of 7 Archive leaderboard report
Node Classification AMZ Photo GraphSAGE Accuracy 95.03% #5 of 14 Archive leaderboard report
Node Classification AMZ Photo HH-GraphSAGE Accuracy 94.55% #6 of 14 Archive leaderboard report
Node Classification AMZ Photo HH-GCN Accuracy 94.52% #7 of 14 Archive leaderboard report
Node Classification AMZ Photo GCN Accuracy 93.59% #9 of 14 Archive leaderboard report
Node Classification Chameleon (60%/20%/20% random splits) HH-GraphSAGE 1:1 Accuracy 62.98 ± 3.35 #23 of 38 Archive leaderboard report
Node Classification Chameleon (60%/20%/20% random splits) HH-GAT 1:1 Accuracy 61.12 ± 1.83 #28 of 38 Archive leaderboard report
Node Classification Chameleon (60%/20%/20% random splits) HH-GCN 1:1 Accuracy 60.24 ± 1.93 #32 of 38 Archive leaderboard report
Node Classification Coauthor CS HH-GraphSAGE Accuracy 95.13% #12 of 24 Archive leaderboard report
Node Classification Coauthor CS GraphSAGE Accuracy 95.11% #13 of 24 Archive leaderboard report
Node Classification Coauthor CS HH-GCN Accuracy 94.71% #16 of 24 Archive leaderboard report
Node Classification Coauthor CS GCN Accuracy 94.06% #17 of 24 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) HH-GraphSAGE 1:1 Accuracy 74.6 ± 6.06 #27 of 36 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) HH-GAT 1:1 Accuracy 72.7 ± 4.26 #29 of 36 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) HH-GCN 1:1 Accuracy 63.24 ± 5.43 #34 of 36 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) HH-GCN 1:1 Accuracy 47.19 ± 1.21 #19 of 37 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) HH-GAT 1:1 Accuracy 46.35 ± 1.86 #21 of 37 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) HH-GraphSAGE 1:1 Accuracy 45.25 ± 1.52 #22 of 37 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) HH-GraphSAGE 1:1 Accuracy 85.95 ± 6.42 #21 of 36 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) HH-GAT 1:1 Accuracy 80.54 ± 4.80 #30 of 36 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) HH-GCN 1:1 Accuracy 71.89 ± 3.46 #35 of 36 Archive leaderboard report
Node Classification Wiki-CS GraphSAGE Accuracy 83.67 #2 of 6 Archive leaderboard report
Node Classification Wiki-CS HH-GraphSAGE Accuracy 82.81 #3 of 6 Archive leaderboard report
Node Classification Wiki-CS HH-GCN Accuracy 82.57 #4 of 6 Archive leaderboard report
Node Classification Wiki-CS GCN Accuracy 81.93 #5 of 6 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) HH-GraphSAGE 1:1 Accuracy 85.88 ± 3.99 #21 of 35 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) HH-GAT 1:1 Accuracy 83.53 ± 3.84 #22 of 35 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) HH-GCN 1:1 Accuracy 79.8 ± 4.30 #24 of 35 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.

Methods

fail

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