Papers › Simplifying Subgraph Representation Learning for Scalable Link Prediction

Simplifying Subgraph Representation Learning for Scalable Link Prediction

29 Jan 2023arXiv:2301.12562archive 2025-07-28

Paul Louis, Shweta Ann Jacob, Amirali Salehi-Abari

Link prediction on graphs is a fundamental problem. Subgraph representation learning approaches (SGRLs), by transforming link prediction to graph classification on the subgraphs around the links, have achieved state-of-the-art performance in link prediction. However, SGRLs are computationally expensive, and not scalable to large-scale graphs due to expensive subgraph-level operations. To unlock the scalability of SGRLs, we propose a new class of SGRLs, that we call Scalable Simplified SGRL (S3GRL). Aimed at faster training and inference, S3GRL simplifies the message passing and aggregation operations in each link's subgraph. S3GRL, as a scalability framework, accommodates various subgraph sampling strategies and diffusion operators to emulate computationally-expensive SGRLs. We propose multiple instances of S3GRL and empirically study them on small to large-scale graphs. Our extensive experiments demonstrate that the proposed S3GRL models scale up SGRLs without significant performance compromise (even with considerable gains in some cases), while offering substantially lower computational footprints (e.g., multi-fold inference and training speedup).

PaperPDFCode

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.

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

Code

venomouscyanide/s3grl officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
venomouscyanide/s3grl_ogb officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting Semi-Supervised Learning with Graph Embeddings (arXiv:1603.08861; that paper's own run record: 15 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 2 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
venomouscyanide/S3GRL_OGB mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Revisiting Semi-Supervised Learning with Graph Embeddings (arXiv:1603.08861; that paper's own run record: 15 ran (of which 4 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 2 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. 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

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

Tasks

Graph ClassificationGraph LearningGraph Representation LearningLink PredictionPredictionRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-citation2 S3GRL (PoS Plus) Ext. data No #9 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 S3GRL (PoS Plus) Number of params 142275001 #9 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 S3GRL (PoS Plus) Test MRR 0.8814 ± 0.0008 #9 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 S3GRL (PoS Plus) Validation MRR 0.8809 ± 0.0074 #9 of 23 Archive leaderboard report
Link Property Prediction ogbl-collab S3GRL (PoS Plus) Ext. data No #11 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab S3GRL (PoS Plus) Number of params 5913025 #11 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab S3GRL (PoS Plus) Test Hits@50 0.6683 ± 0.0030 #11 of 34 Archive leaderboard report
Link Property Prediction ogbl-collab S3GRL (PoS Plus) Validation Hits@50 0.9861 ± 0.0006 #11 of 34 Archive leaderboard report
Link Property Prediction ogbl-ppa S3GRL (PoS Plus) Ext. data No #16 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa S3GRL (PoS Plus) Number of params 32270001 #16 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa S3GRL (PoS Plus) Test Hits@100 0.4242 ± 0.0180 #16 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa S3GRL (PoS Plus) Validation Hits@100 0.6512 ± 0.0109 #16 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