{"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/norm-range-partition-a-universal-catalyst-for","title":"Norm-Range Partition: A Universal Catalyst for LSH based Maximum Inner Product Search (MIPS)","arxiv_id":"1810.09104","date":"2018-10-22","proceeding":null,"authors":["Xiao Yan","Xinyan Dai","Jie Liu","Kaiwen Zhou","James Cheng"],"abstract":"Recently, locality sensitive hashing (LSH) was shown to be effective for MIPS\nand several algorithms including $L_2$-ALSH, Sign-ALSH and Simple-LSH have been\nproposed. In this paper, we introduce the norm-range partition technique, which\npartitions the original dataset into sub-datasets containing items with similar\n2-norms and builds hash index independently for each sub-dataset. We prove that\nnorm-range partition reduces the query processing complexity for all existing\nLSH based MIPS algorithms under mild conditions. The key to performance\nimprovement is that norm-range partition allows to use smaller normalization\nfactor most sub-datasets. For efficient query processing, we also formulate a\nunified framework to rank the buckets from the hash indexes of different\nsub-datasets. Experiments on real datasets show that norm-range partition\nsignificantly reduces the number of probed for LSH based MIPS algorithms when\nachieving the same recall.","url_abs":"http://arxiv.org/abs/1810.09104v2","url_pdf":"http://arxiv.org/pdf/1810.09104v2.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":"norm-range-partition-a-universal-catalyst-for","repo_url":"https://github.com/xinyandai/similarity-search","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"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}