{"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/binary-latent-representations-for-efficient","title":"Binary Latent Representations for Efficient Ranking: Empirical Assessment","arxiv_id":"1706.07479","date":"2017-06-22","proceeding":null,"authors":["Maciej Kula"],"abstract":"Large-scale recommender systems often face severe latency and storage\nconstraints at prediction time. These are particularly acute when the number of\nitems that could be recommended is large, and calculating predictions for the\nfull set is computationally intensive. In an attempt to relax these\nconstraints, we train recommendation models that use binary rather than\nreal-valued user and item representations, and show that while they are\nsubstantially faster to evaluate, the gains in speed come at a large cost in\naccuracy. In our Movielens 1M experiments, we show that reducing the latent\ndimensionality of traditional models offers a more attractive accuracy/speed\ntrade-off than using binary representations.","url_abs":"http://arxiv.org/abs/1706.07479v2","url_pdf":"http://arxiv.org/pdf/1706.07479v2.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":"binary-latent-representations-for-efficient","repo_url":"https://github.com/maciejkula/binge","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"binary-latent-representations-for-efficient","repo_url":"https://github.com/Santosh-Gupta/Research2Vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}