{"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/scalable-cross-entropy-loss-for-sequential","title":"Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs","arxiv_id":"2409.18721","date":"2024-09-27","proceeding":null,"authors":["Gleb Mezentsev","Danil Gusak","Ivan Oseledets","Evgeny Frolov"],"abstract":"Scalability issue plays a crucial role in productionizing modern recommender systems. Even lightweight architectures may suffer from high computational overload due to intermediate calculations, limiting their practicality in real-world applications. Specifically, applying full Cross-Entropy (CE) loss often yields state-of-the-art performance in terms of recommendations quality. Still, it suffers from excessive GPU memory utilization when dealing with large item catalogs. This paper introduces a novel Scalable Cross-Entropy (SCE) loss function in the sequential learning setup. It approximates the CE loss for datasets with large-size catalogs, enhancing both time efficiency and memory usage without compromising recommendations quality. Unlike traditional negative sampling methods, our approach utilizes a selective GPU-efficient computation strategy, focusing on the most informative elements of the catalog, particularly those most likely to be false positives. This is achieved by approximating the softmax distribution over a subset of the model outputs through the maximum inner product search. Experimental results on multiple datasets demonstrate the effectiveness of SCE in reducing peak memory usage by a factor of up to 100 compared to the alternatives, retaining or even exceeding their metrics values. The proposed approach also opens new perspectives for large-scale developments in different domains, such as large language models.","url_abs":"https://arxiv.org/abs/2409.18721v2","url_pdf":"https://arxiv.org/pdf/2409.18721v2.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":"scalable-cross-entropy-loss-for-sequential","repo_url":"https://github.com/AIRI-Institute/Scalable-SASRec","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"sequential-recommendation","task_name":"Sequential Recommendation"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sequential-recommendation-on-amazon-beauty-1","task":"Sequential Recommendation","dataset":"Amazon Beauty","model":"SASRec-SCE","rank_in_archive_order":1,"of":1,"metrics":{"HR@10":"0.0935","NDCG@10":"0.0544"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-recommendation-on-behance","task":"Sequential Recommendation","dataset":"Behance","model":"SASRec-SCE","rank_in_archive_order":1,"of":1,"metrics":{"COV@1":"0.0393","COV@10":"0.25","COV@5":"15.3","HR@10":"0.113","HR@5":"0.0853","NDCG@1":"0.0277","NDCG@10":"0.0663","NDCG@5":"0.0572"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-recommendation-on-gowalla","task":"Sequential Recommendation","dataset":"Gowalla","model":"SASRec-SCE","rank_in_archive_order":1,"of":1,"metrics":{"COV@1":"0.0304","COV@10":"0.2190","COV@5":"0.126","HR@10":"0.0831","HR@5":"0.0574","NDCG@1":"0.0207","NDCG@10":"0.0476","NDCG@5":"0.0393"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}