{"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/optimization-of-indexing-based-on-k-nearest","title":"Optimization of Indexing Based on k-Nearest Neighbor Graph for Proximity Search in High-dimensional Data","arxiv_id":"1810.07355","date":"2018-10-17","proceeding":null,"authors":["Masajiro Iwasaki","Daisuke Miyazaki"],"abstract":"Searching for high-dimensional vector data with high accuracy is an\ninevitable search technology for various types of data. Graph-based indexes are\nknown to reduce the query time for high-dimensional data. To further improve\nthe query time by using graphs, we focused on the indegrees and outdegrees of\ngraphs. While a sufficient number of incoming edges (indegrees) are\nindispensable for increasing search accuracy, an excessive number of outgoing\nedges (outdegrees) should be suppressed so as to not increase the query time.\nTherefore, we propose three degree-adjustment methods: static degree adjustment\nof not only outdegrees but also indegrees, dynamic degree adjustment with which\noutdegrees are determined by the search accuracy users require, and path\nadjustment to remove edges that have alternative search paths to reduce\noutdegrees. We also show how to obtain optimal degree-adjustment parameters and\nthat our methods outperformed previous methods for image and textual data.","url_abs":"http://arxiv.org/abs/1810.07355v1","url_pdf":"http://arxiv.org/pdf/1810.07355v1.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":"optimization-of-indexing-based-on-k-nearest","repo_url":"https://github.com/yahoojapan/NGT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"optimization-of-indexing-based-on-k-nearest","repo_url":"https://github.com/Lsyhprum/WEAVESS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.07355","atlas_url":"https://app.syntology.ai/?focus=1810.07355","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}