arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.12751cs.IRcs.DBcs.DScs.LG
收藏

SAH:面向逆向 $k$-最大内积搜索的感知偏移的非对称哈希

SAH: Shifting-aware Asymmetric Hashing for Reverse $k$-Maximum Inner Product Search

School of Computing, National University of Singapore(新加坡国立大学计算机学院);School of Data Science and Engineering, East China Normal University(华东师范大学数据科学与工程学院)

Qiang Huang, Yanhao Wang, Anthony K. H. Tung

AI总结:

本文研究逆向 $k$-最大内积搜索问题,提出次二次时间算法 SAH,通过设计偏移不变的非对称变换与基于 Cone-Tree 的阻塞策略加速搜索,在五个真实数据集上比现有方法快4-8倍且F1超90%。

摘要:

本文研究了一个新且具挑战性的问题,称为逆向 $k$-最大内积搜索(R$k$MIPS)。给定一个查询(物品)向量、一组物品向量和一组用户向量,R$k$MIPS 问题旨在找到一组用户向量,这些用户向量与查询向量的内积是查询向量和物品向量之间 $k$ 个最大内积之一。我们提出了首个次二次时间算法,即感知偏移的非对称哈希(SAH),来解决 R$k$MIPS 问题。为了加速物品向量上的最大内积搜索(MIPS),我们设计了一种偏移不变的非对称变换,并开发了一种新颖的次线性时间感知偏移的非对称局部敏感哈希(SA-ALSH)方案。此外,我们设计了一种基于 Cone-Tree 的新阻塞策略,以有效地(批量)修剪用户向量。我们证明 SAH 在解决 RMIPS 问题上具有理论保证。在五个真实世界数据集上的实验结果表明,SAH 的运行速度比最先进的 R$k$MIPS 方法快 4$\sim$8$\times$,同时 F1-scores 超过 90\\%。代码可在 \url{https://github.com/HuangQiang/SAH} 获取。

英文摘要:

This paper investigates a new yet challenging problem called Reverse $k$-Maximum Inner Product Search (R$k$MIPS). Given a query (item) vector, a set of item vectors, and a set of user vectors, the problem of R$k$MIPS aims to find a set of user vectors whose inner products with the query vector are one of the $k$ largest among the query and item vectors. We propose the first subquadratic-time algorithm, i.e., Shifting-aware Asymmetric Hashing (SAH), to tackle the R$k$MIPS problem. To speed up the Maximum Inner Product Search (MIPS) on item vectors, we design a shifting-invariant asymmetric transformation and develop a novel sublinear-time Shifting-Aware Asymmetric Locality Sensitive Hashing (SA-ALSH) scheme. Furthermore, we devise a new blocking strategy based on the Cone-Tree to effectively prune user vectors (in a batch). We prove that SAH achieves a theoretical guarantee for solving the RMIPS problem. Experimental results on five real-world datasets show that SAH runs 4$\sim$8$\times$ faster than the state-of-the-art methods for R$k$MIPS while achieving F1-scores of over 90\%. The code is available at \url{https://github.com/HuangQiang/SAH}.

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。

↑