arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.26474cs.DBcs.IR
收藏

广义范围过滤近似最近邻搜索:包含与重叠 [技术报告]

Generalized Range Filtering Approximate Nearest Neighbor Search: Containment and Overlap [Technical Report]

Xidian University(西安电子科技大学);The Chinese University of Hong Kong(香港中文大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Xi’an University of Posts and Telecommunications(西安邮电大学)

Yingfan Liu, Tong Wu, Jiadong Xie, Yang Zhao, Jeffrey Xu Yu, Jiangtao Cui

AI总结:

针对带有数值范围属性的向量,提出多段树图方法,支持任意范围-范围谓词(包含、重叠等)的近似最近邻搜索,在保持索引大小和构建时间与现有方法相当的同时,实现了高达12.5倍的加速。

摘要:

带有范围过滤的近似最近邻(ANN)搜索最近引起了广泛关注。本文深入研究了该问题的一种广义形式,即对范围值属性进行精确范围-范围(RR)谓词的ANN搜索,称为RR过滤ANN(RRANN)。具体来说,给定$\mathbb{R}^d$中的$n$个向量,每个向量$v_i$关联一个数值范围$[l_i, r_i]$,表示价格范围或时间间隔等。RRANN查询$(v_q, l_q, r_q)$旨在找到与$v_q$最近的$k$个向量,这些向量满足查询范围$[l_q, r_q]$与对象范围$[l_i, r_i]$之间定义的任意RR谓词。RR谓词未指定,允许用户定义条件。它可以包含包含($[l_i, r_i] \subseteq [l_q, r_q]$或$[l_q, r_q] \subseteq [l_i, r_i]$)、重叠($l_i \le l_q \le r_i \le r_q$或$l_q \le l_i \le r_q \le r_i$)或它们的析取。RRANN在价格范围或时间间隔相关的查询中具有广泛的应用,并且它推广了现有带有范围过滤的ANN搜索变体。然而,现有的针对这些问题的专用方法缺乏支持任意RR谓词查询的能力。因此,我们引入了一种新方法,称为多段树图。它通过避免遍历不满足谓词的节点,高效地处理任意RR谓词,并保持与RFANN最先进方法相当的索引大小和构建时间。在真实世界数据上的大量实验证明了我们的方法在RRANN查询中的有效性,与基线相比,在相同精度下实现了高达12.5倍的加速。此外,与各自的最先进方法相比,我们的方法在RFANN搜索性能上相当,在IFANN和TSANN搜索性能上显著更优。我们的代码可在https://github.com/FanEDG/MSTG获取。

英文摘要:

Approximate nearest neighbor (ANN) search with range filters has recently garnered significant attention. This paper delves into a generalized form of this problem, i.e., ANN search with exact range-range (RR) predicates on a range-valued attribute, named RR filtering ANN (RRANN). Specifically, given $n$ vectors in $\mathbb{R}^d$, each vector $v_i$ is associated with a numeric range $[l_i, r_i]$, symbolizing aspects like a price range or time interval. An RRANN query $(v_q, l_q, r_q)$ aims at finding $k$ vectors closest to $v_q$ within the vectors satisfying an arbitrary RR predicate defined between the query range $[l_q, r_q]$ and the object range $[l_i, r_i]$. The RR predicate remains unspecified, enabling user-defined conditions. It may encompass containment ($[l_i, r_i] \subseteq [l_q, r_q]$ or $[l_q, r_q] \subseteq [l_i, r_i]$), overlap ($l_i \le l_q \le r_i \le r_q$ or $l_q \le l_i \le r_q \le r_i$), or a disjunction of them. RRANN has broad applications in queries related to price ranges or time intervals, and it generalizes existing variants of ANN search with range filters. However, existing dedicated approaches for these problems lack the capacity to support queries with arbitrary RR predicates. Hence, we introduce a new approach, labeled multi-segment tree graph. It efficiently handles arbitrary RR predicates by avoiding traversal through non-predicate-satisfied nodes, and keeps equivalent index size and construction time to state-of-the-art methods for RFANN. Extensive experiments on real-world data demonstrate the efficacy of our approach in RRANN queries, achieving up to 12.5x speedups with the same accuracy as the baselines. Moreover, our approach attains comparable RFANN search performance and notably superior IFANN and TSANN search performance compared to the respective state-of-the-art approaches. Our code is available at https://github.com/FanEDG/MSTG.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑