Papers › Long-range Meta-path Search on Large-scale Heterogeneous Graphs

Long-range Meta-path Search on Large-scale Heterogeneous Graphs

17 Jul 2023arXiv:2307.08430archive 2025-07-28

Chao Li, Zijie Guo, Qiuting He, Hao Xu, Kun He

Utilizing long-range dependency, a concept extensively studied in homogeneous graphs, remains underexplored in heterogeneous graphs, especially on large ones, posing two significant challenges: Reducing computational costs while maximizing effective information utilization in the presence of heterogeneity, and overcoming the over-smoothing issue in graph neural networks. To address this gap, we investigate the importance of different meta-paths and introduce an automatic framework for utilizing long-range dependency on heterogeneous graphs, denoted as Long-range Meta-path Search through Progressive Sampling (LMSPS). Specifically, we develop a search space with all meta-paths related to the target node type. By employing a progressive sampling algorithm, LMSPS dynamically shrinks the search space with hop-independent time complexity. Through a sampling evaluation strategy, LMSPS conducts a specialized and effective meta-path selection, leading to retraining with only effective meta-paths, thus mitigating costs and over-smoothing. Extensive experiments across diverse heterogeneous datasets validate LMSPS's capability in discovering effective long-range meta-paths, surpassing state-of-the-art methods. Our code is available at https://github.com/JHL-HUST/LMSPS.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2307.08430")

Code

Syntology Ran 3 of 7 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jhl-hust/ldmlp officialmentioned in papermentioned on GitHubpytorch report
jhl-hust/lmsps officialmentioned in papermentioned on GitHubpytorch report
JHL-HUST/LDMLP mentioned on GitHubpytorch report
JHL-HUST/LMSPS mentioned on GitHubpytorch 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

7 samples harvested; 3 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran
4unverified

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 jhl-hust/ldmlp. “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 “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

evaluator jhl-hust/ldmlp/hgb/utils.py official repository ran no licence file found · pointer only · bdd10a0559cd9f67 · report
infer_eval jhl-hust/ldmlp/hgb/utils.py official repository ran no licence file found · pointer only · 76cefceaf1693dd9 · report
project_op jhl-hust/ldmlp/hgb/utils.py official repository ran no licence file found · pointer only · 6e0ca78e6b055583 · report
parse_args jhl-hust/ldmlp/hgb/main_path.py official repository unverified no licence file found · pointer only · 8eb64db85c51b748 · report
parse_args jhl-hust/ldmlp/hgb/train_search.py official repository unverified no licence file found · pointer only · d3e41752dea9554e · report
parse_args jhl-hust/ldmlp/ogbn/main_path.py official repository unverified no licence file found · pointer only · 87498f3a0ca6b721 · report
parse_args jhl-hust/ldmlp/ogbn/main_path_nested.py official repository unverified no licence file found · pointer only · 423bc5659e28c499 · report

Tasks

Node ClassificationNode Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Property Prediction ogbn-mag LMSPS (w/o embs) Ext. data No #4 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LMSPS (w/o embs) Number of params 16470044 #4 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LMSPS (w/o embs) Test Accuracy 0.5784 ± 0.0022 #4 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LMSPS (w/o embs) Validation Accuracy 0.5951 ± 0.0007 #4 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LMSPS(w/o ComplEx embs) Ext. data No #6 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LMSPS(w/o ComplEx embs) Number of params 16470044 #6 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LMSPS(w/o ComplEx embs) Test Accuracy 0.5767 ± 0.0015 #6 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LMSPS(w/o ComplEx embs) Validation Accuracy 0.5902 ± 0.0016 #6 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LDMLP(w/o ComplEx embs) Ext. data No #9 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LDMLP(w/o ComplEx embs) Number of params 13177884 #9 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LDMLP(w/o ComplEx embs) Test Accuracy 0.5739 ± 0.0012 #9 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag LDMLP(w/o ComplEx embs) Validation Accuracy 0.5888 ± 0.0015 #9 of 39 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