{"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/representation-learning-and-pairwise-ranking","title":"Representation Learning and Pairwise Ranking for Implicit Feedback in Recommendation Systems","arxiv_id":"1705.00105","date":"2017-04-29","proceeding":null,"authors":["Sumit Sidana","Mikhail Trofimov","Oleg Horodnitskii","Charlotte Laclau","Yury Maximov","Massih-Reza Amini"],"abstract":"In this paper, we propose a novel ranking framework for collaborative\nfiltering with the overall aim of learning user preferences over items by\nminimizing a pairwise ranking loss. We show the minimization problem involves\ndependent random variables and provide a theoretical analysis by proving the\nconsistency of the empirical risk minimization in the worst case where all\nusers choose a minimal number of positive and negative items. We further derive\na Neural-Network model that jointly learns a new representation of users and\nitems in an embedded space as well as the preference relation of users over the\npairs of items. The learning objective is based on three scenarios of ranking\nlosses that control the ability of the model to maintain the ordering over the\nitems induced from the users' preferences, as well as, the capacity of the\ndot-product defined in the learned embedded space to produce the ordering. The\nproposed model is by nature suitable for implicit feedback and involves the\nestimation of only very few parameters. Through extensive experiments on\nseveral real-world benchmarks on implicit data, we show the interest of\nlearning the preference and the embedding simultaneously when compared to\nlearning those separately. We also demonstrate that our approach is very\ncompetitive with the best state-of-the-art collaborative filtering techniques\nproposed for implicit feedback.","url_abs":"http://arxiv.org/abs/1705.00105v4","url_pdf":"http://arxiv.org/pdf/1705.00105v4.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":"representation-learning-and-pairwise-ranking","repo_url":"https://github.com/sumitsidana/NERvE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}