{"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/reconfigurable-inverted-index","title":"Reconfigurable Inverted Index","arxiv_id":"1808.03969","date":"2018-08-12","proceeding":null,"authors":["Yusuke Matsui","Ryota Hinami","Shin'ichi Satoh"],"abstract":"Existing approximate nearest neighbor search systems suffer from two\nfundamental problems that are of practical importance but have not received\nsufficient attention from the research community. First, although existing\nsystems perform well for the whole database, it is difficult to run a search\nover a subset of the database. Second, there has been no discussion concerning\nthe performance decrement after many items have been newly added to a system.\nWe develop a reconfigurable inverted index (Rii) to resolve these two issues.\nBased on the standard IVFADC system, we design a data layout such that items\nare stored linearly. This enables us to efficiently run a subset search by\nswitching the search method to a linear PQ scan if the size of a subset is\nsmall. Owing to the linear layout, the data structure can be dynamically\nadjusted after new items are added, maintaining the fast speed of the system.\nExtensive comparisons show that Rii achieves a comparable performance with\nstate-of-the art systems such as Faiss.","url_abs":"http://arxiv.org/abs/1808.03969v1","url_pdf":"http://arxiv.org/pdf/1808.03969v1.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":"reconfigurable-inverted-index","repo_url":"https://github.com/matsui528/rii","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}