arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.02057cs.DB
收藏

QVCache: 一种查询感知的向量缓存

QVCache: A Query-Aware Vector Cache

ETH Zurich(苏黎世联邦理工学院);EPFL(洛桑联邦理工学院)

Anıl Eren Göçer, Ioanna Tsakalidou, Hamish Nicholson, Kyoungmin Kim, Anastasia Ailamaki

AI总结:

QVCache是一种查询感知的向量缓存系统,通过语义相似性缓存和动态阈值学习,有效降低查询延迟并提升向量搜索效率。

摘要:

向量数据库已成为现代信息检索的核心,驱动推荐、搜索和检索增强生成(RAG)管道等应用。然而,将近似最近邻(ANN)搜索扩展到高召回率的同时满足严格延迟SLA仍受到内存容量和I/O带宽的根本限制。基于磁盘的向量搜索系统在高精度时会出现严重的延迟下降,而全内存解决方案在十亿级数据时会带来高昂的内存成本。尽管缓存在传统数据库中扮演着核心角色,但向量搜索缺乏一个通用的查询级缓存层,能够摊销重复查询的工作量。我们提出了QVCache,这是第一个后端无关、查询级缓存系统,用于具有有限内存足迹的ANN搜索。QVCache通过执行语义查询重复进行相似性感知缓存,而不是精确匹配查找。它动态学习区域特定的距离阈值,使用在线学习算法,从而在保持召回率的同时实现缓存命中,同时将查找延迟和内存使用独立于数据集大小进行限制。QVCache作为现有向量数据库的滴入层运行。它维护了兆字节级的内存足迹,并实现了亚毫秒级的缓存命中延迟,当与现有ANN系统集成时,可将端到端查询延迟降低高达40至1000倍。对于表现出时间-语义局部性的负载,QVCache显著减少延迟,同时保持与底层ANN后端相当的召回率,使其成为可扩展向量搜索缺失但必要的缓存层。

英文摘要:

Vector databases have become a cornerstone of modern information retrieval, powering applications in recommendation, search, and retrieval-augmented generation (RAG) pipelines. However, scaling approximate nearest neighbor (ANN) search to high recall under strict latency SLOs remains fundamentally constrained by memory capacity and I/O bandwidth. Disk-based vector search systems suffer severe latency degradation at high accuracy, while fully in-memory solutions incur prohibitive memory costs at billion-scale. Despite the central role of caching in traditional databases, vector search lacks a general query-level caching layer capable of amortizing repeated query work. We present QVCache, the first backend-agnostic, query-level caching system for ANN search with bounded memory footprint. QVCache exploits semantic query repetition by performing similarity-aware caching rather than exact-match lookup. It dynamically learns region-specific distance thresholds using an online learning algorithm, enabling recall-preserving cache hits while bounding lookup latency and memory usage independently of dataset size. QVCache operates as a drop-in layer for existing vector databases. It maintains a megabyte-scale memory footprint and achieves sub-millisecond cache-hit latency, reducing end-to-end query latency by up to 40-1000x when integrated with existing ANN systems. For workloads exhibiting temporal-semantic locality, QVCache substantially reduces latency while preserving recall comparable to the underlying ANN backend, establishing it as a missing but essential caching layer for scalable vector search.

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。

↑