最近邻搜索
计算机科学
对数
等级制度
缩放比例
图形
公制(单位)
度量空间
k-最近邻算法
算法
理论计算机科学
数学
数据挖掘
人工智能
离散数学
几何学
市场经济
数学分析
经济
运营管理
作者
Yu. A. Malkov,D. A. Yashunin
标识
DOI:10.1109/tpami.2018.2889473
摘要
We present a new approach for the approximate K-nearest neighbor search based on navigable small world graphs with controllable hierarchy (Hierarchical NSW, HNSW). The proposed solution is fully graph-based, without any need for additional search structures (typically used at the coarse search stage of the most proximity graph techniques). Hierarchical NSW incrementally builds a multi-layer structure consisting of a hierarchical set of proximity graphs (layers) for nested subsets of the stored elements. The maximum layer in which an element is present is selected randomly with an exponentially decaying probability distribution. This allows producing graphs similar to the previously studied Navigable Small World (NSW) structures while additionally having the links separated by their characteristic distance scales. Starting the search from the upper layer together with utilizing the scale separation boosts the performance compared to NSW and allows a logarithmic complexity scaling. Additional employment of a heuristic for selecting proximity graph neighbors significantly increases performance at high recall and in case of highly clustered data. Performance evaluation has demonstrated that the proposed general metric space search index is able to strongly outperform previous opensource state-of-the-art vector-only approaches. Similarity of the algorithm to the skip list structure allows straightforward balanced distributed implementation.
科研通智能强力驱动
Strongly Powered by AbleSci AI