{"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-ranging-lsh-for-maximum-inner-product","title":"Norm-Ranging LSH for Maximum Inner Product Search","arxiv_id":"1809.08782","date":"2018-09-24","proceeding":"NeurIPS 2018 12","authors":["Xiao Yan","Jinfeng Li","Xinyan Dai","Hongzhi Chen","James Cheng"],"abstract":"Neyshabur and Srebro proposed Simple-LSH, which is the state-of-the-art\nhashing method for maximum inner product search (MIPS) with performance\nguarantee. We found that the performance of Simple-LSH, in both theory and\npractice, suffers from long tails in the 2-norm distribution of real datasets.\nWe propose Norm-ranging LSH, which addresses the excessive normalization\nproblem caused by long tails in Simple-LSH by partitioning a dataset into\nmultiple sub-datasets and building a hash index for each sub-dataset\nindependently. We prove that Norm-ranging LSH has lower query time complexity\nthan Simple-LSH. We also show that the idea of partitioning the dataset can\nimprove other hashing based methods for MIPS. To support efficient query\nprocessing on the hash indexes of the sub-datasets, a novel similarity metric\nis formulated. Experiments show that Norm-ranging LSH achieves an order of\nmagnitude speedup over Simple-LSH for the same recall, thus significantly\nbenefiting applications that involve MIPS.","url_abs":"http://arxiv.org/abs/1809.08782v2","url_pdf":"http://arxiv.org/pdf/1809.08782v2.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-ranging-lsh-for-maximum-inner-product","repo_url":"https://github.com/xinyandai/similarity-search","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.08782","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}