{"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-representation-learning-and","title":"Lightweight representation learning for efficient and scalable recommendation","arxiv_id":"2101.00870","date":"2021-01-04","proceeding":null,"authors":["Olivier Koch","Amine Benhalloum","Guillaume Genthial","Denis Kuzin","Dmitry Parfenchik"],"abstract":"Over the past decades, recommendation has become a critical component of many online services such as media streaming and e-commerce. Recent advances in algorithms, evaluation methods and datasets have led to continuous improvements of the state-of-the-art. However, much work remains to be done to make these methods scale to the size of the internet. Online advertising offers a unique testbed for recommendation at scale. Every day, billions of users interact with millions of products in real-time. Systems addressing this scenario must work reliably at scale. We propose an efficient model (LED, for Lightweight Encoder-Decoder) reaching a new trade-off between complexity, scale and performance. Specifically, we show that combining large-scale matrix factorization with lightweight embedding fine-tuning unlocks state-of-the-art performance at scale. We further provide the detailed description of a system architecture and demonstrate its operation over two months at the scale of the internet. Our design allows serving billions of users across hundreds of millions of items in a few milliseconds using standard hardware.","url_abs":"https://arxiv.org/abs/2101.00870v2","url_pdf":"https://arxiv.org/pdf/2101.00870v2.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-representation-learning-and","repo_url":"https://github.com/criteo/deepr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/collaborative-filtering-on-movielens-20m","task":"Recommendation Systems","dataset":"MovieLens 20M","model":"LED","rank_in_archive_order":14,"of":18,"metrics":{"Recall@20":"0.375","Recall@50":"0.516"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2101.00870","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}