{"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/reconsidering-the-performance-of-gae-in-link","title":"Reconsidering the Performance of GAE in Link Prediction","arxiv_id":"2411.03845","date":"2024-11-06","proceeding":null,"authors":["Weishuo Ma","Yanbo Wang","Xiyuan Wang","Muhan Zhang"],"abstract":"Various graph neural networks (GNNs) with advanced training techniques and model designs have been proposed for link prediction tasks. However, outdated baseline models may lead to an overestimation of the benefits provided by these novel approaches. To address this, we systematically investigate the potential of Graph Autoencoders (GAE) by meticulously tuning hyperparameters and utilizing the trick of orthogonal embedding and linear propagation. Our findings reveal that a well-optimized GAE can match the performance of more complex models while offering greater computational efficiency.","url_abs":"https://arxiv.org/abs/2411.03845v1","url_pdf":"https://arxiv.org/pdf/2411.03845v1.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":"reconsidering-the-performance-of-gae-in-link","repo_url":"https://github.com/graphpku/refined-gae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"reconsidering-the-performance-of-gae-in-link","repo_url":"https://github.com/GraphPKU/Refined-GAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-property-prediction-on-ogbl-collab","task":"Link Property Prediction","dataset":"ogbl-collab","model":"Refined-GAE","rank_in_archive_order":9,"of":34,"metrics":{"Ext. data":"No","Number of params":"126669825","Test Hits@50":"0.6816 ± 0.0041","Validation Hits@50":"1.0000 ± 0.0000"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-ddi","task":"Link Property Prediction","dataset":"ogbl-ddi","model":"Refined-GAE","rank_in_archive_order":6,"of":31,"metrics":{"Ext. data":"No","Number of params":"13816833","Test Hits@20":"0.9443 ± 0.0057","Validation Hits@20":"0.7979 ± 0.0159"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-ppa","task":"Link Property Prediction","dataset":"ogbl-ppa","model":"Refined-GAE","rank_in_archive_order":2,"of":26,"metrics":{"Ext. data":"No","Number of params":"295848449","Test Hits@100":"0.7334 ± 0.0092","Validation Hits@100":"0.7391 ± 0.0178"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.03845","atlas_url":"https://app.syntology.ai/?focus=2411.03845","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}