{"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/low-rank-factorization-of-determinantal-point","title":"Low-Rank Factorization of Determinantal Point Processes for Recommendation","arxiv_id":"1602.05436","date":"2016-02-17","proceeding":null,"authors":["Mike Gartrell","Ulrich Paquet","Noam Koenigstein"],"abstract":"Determinantal point processes (DPPs) have garnered attention as an elegant\nprobabilistic model of set diversity. They are useful for a number of subset\nselection tasks, including product recommendation. DPPs are parametrized by a\npositive semi-definite kernel matrix. In this work we present a new method for\nlearning the DPP kernel from observed data using a low-rank factorization of\nthis kernel. We show that this low-rank factorization enables a learning\nalgorithm that is nearly an order of magnitude faster than previous approaches,\nwhile also providing for a method for computing product recommendation\npredictions that is far faster (up to 20x faster or more for large item\ncatalogs) than previous techniques that involve a full-rank DPP kernel.\nFurthermore, we show that our method provides equivalent or sometimes better\npredictive performance than prior full-rank DPP approaches, and better\nperformance than several other competing recommendation methods in many cases.\nWe conduct an extensive experimental evaluation using several real-world\ndatasets in the domain of product recommendation to demonstrate the utility of\nour method, along with its limitations.","url_abs":"http://arxiv.org/abs/1602.05436v1","url_pdf":"http://arxiv.org/pdf/1602.05436v1.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":"low-rank-factorization-of-determinantal-point","repo_url":"https://github.com/mankmonjre/k-DPP-reco-engine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"point-processes","task_name":"Point Processes"},{"task_slug":"product-recommendation","task_name":"Product Recommendation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1602.05436","atlas_url":"https://app.syntology.ai/?focus=1602.05436","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}