{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/simplifying-subgraph-representation-learning","title":"Simplifying Subgraph Representation Learning for Scalable Link Prediction","arxiv_id":"2301.12562","date":"2023-01-29","proceeding":null,"authors":["Paul Louis","Shweta Ann Jacob","Amirali Salehi-Abari"],"abstract":"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).","url_abs":"https://arxiv.org/abs/2301.12562v4","url_pdf":"https://arxiv.org/pdf/2301.12562v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"simplifying-subgraph-representation-learning","repo_url":"https://github.com/venomouscyanide/s3grl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"simplifying-subgraph-representation-learning","repo_url":"https://github.com/venomouscyanide/s3grl_ogb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"simplifying-subgraph-representation-learning","repo_url":"https://github.com/venomouscyanide/S3GRL_OGB","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-property-prediction-on-ogbl-citation2","task":"Link Property Prediction","dataset":"ogbl-citation2","model":"S3GRL (PoS Plus)","rank_in_archive_order":9,"of":23,"metrics":{"Ext. data":"No","Number of params":"142275001","Test MRR":"0.8814 ± 0.0008","Validation MRR":"0.8809 ± 0.0074"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-collab","task":"Link Property Prediction","dataset":"ogbl-collab","model":"S3GRL (PoS Plus)","rank_in_archive_order":11,"of":34,"metrics":{"Ext. data":"No","Number of params":"5913025","Test Hits@50":"0.6683 ± 0.0030","Validation Hits@50":"0.9861 ± 0.0006"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-ppa","task":"Link Property Prediction","dataset":"ogbl-ppa","model":"S3GRL (PoS Plus)","rank_in_archive_order":16,"of":26,"metrics":{"Ext. data":"No","Number of params":"32270001","Test Hits@100":"0.4242 ± 0.0180","Validation Hits@100":"0.6512 ± 0.0109"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.12562","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}