{"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/beyond-greedy-ranking-slate-optimization-via","title":"Beyond Greedy Ranking: Slate Optimization via List-CVAE","arxiv_id":"1803.01682","date":"2018-03-05","proceeding":"ICLR 2019 5","authors":["Ray Jiang","Sven Gowal","Timothy A. Mann","Danilo J. Rezende"],"abstract":"The conventional solution to the recommendation problem greedily ranks\nindividual document candidates by prediction scores. However, this method fails\nto optimize the slate as a whole, and hence, often struggles to capture biases\ncaused by the page layout and document interdepedencies. The slate\nrecommendation problem aims to directly find the optimally ordered subset of\ndocuments (i.e. slates) that best serve users' interests. Solving this problem\nis hard due to the combinatorial explosion in all combinations of document\ncandidates and their display positions on the page. Therefore we propose a\nparadigm shift from the traditional viewpoint of solving a ranking problem to a\ndirect slate generation framework. In this paper, we introduce List Conditional\nVariational Auto-Encoders (List-CVAE), which learns the joint distribution of\ndocuments on the slate conditioned on user responses, and directly generates\nfull slates. Experiments on simulated and real-world data show that List-CVAE\noutperforms popular comparable ranking methods consistently on various scales\nof documents corpora.","url_abs":"http://arxiv.org/abs/1803.01682v6","url_pdf":"http://arxiv.org/pdf/1803.01682v6.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":"beyond-greedy-ranking-slate-optimization-via","repo_url":"https://github.com/ferendo/RecommendationSystem","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}