{"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/discrete-factorization-machines-for-fast","title":"Discrete Factorization Machines for Fast Feature-based Recommendation","arxiv_id":"1805.02232","date":"2018-05-06","proceeding":null,"authors":["Han Liu","Xiangnan He","Fuli Feng","Liqiang Nie","Rui Liu","Hanwang Zhang"],"abstract":"User and item features of side information are crucial for accurate\nrecommendation. However, the large number of feature dimensions, e.g., usually\nlarger than 10^7, results in expensive storage and computational cost. This\nprohibits fast recommendation especially on mobile applications where the\ncomputational resource is very limited. In this paper, we develop a generic\nfeature-based recommendation model, called Discrete Factorization Machine\n(DFM), for fast and accurate recommendation. DFM binarizes the real-valued\nmodel parameters (e.g., float32) of every feature embedding into binary codes\n(e.g., boolean), and thus supports efficient storage and fast user-item score\ncomputation. To avoid the severe quantization loss of the binarization, we\npropose a convergent updating rule that resolves the challenging discrete\noptimization of DFM. Through extensive experiments on two real-world datasets,\nwe show that 1) DFM consistently outperforms state-of-the-art binarized\nrecommendation models, and 2) DFM shows very competitive performance compared\nto its real-valued version (FM), demonstrating the minimized quantization loss.\nThis work is accepted by IJCAI 2018.","url_abs":"http://arxiv.org/abs/1805.02232v3","url_pdf":"http://arxiv.org/pdf/1805.02232v3.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":"discrete-factorization-machines-for-fast","repo_url":"https://github.com/hanliu95/DFM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"binarization","task_name":"Binarization"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.02232","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}