Aker：面向向量搜索的密度感知近似缓存（扩展版）
Aker: Density-Aware Approximate Caching for Vector Search (Extended Version)
- KAIST（韩国科学技术院）
- Microsoft Research（微软研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
Aker是面向磁盘ANNS的密度感知近似缓存，通过动态调整相似度阈值与del-consistency一致性模型，提升了召回率与QPS，内存占用仅为pgvector共享缓冲区的0.6倍。
AI中文摘要：
基于磁盘的近似最近邻搜索（ANNS）因索引遍历过程中频繁访问磁盘而产生高I/O开销。近似缓存通过复用过往查询结果为后续相似查询提供服务，是规避昂贵磁盘搜索的可行方案。然而现有方法存在两大关键局限：其一，其近似命中谓词无法同时实现高吞吐量与高准确率，原因在于它们未适配高维空间中变化的局部邻域密度；其二，它们缺乏有效的刷新机制以在向量更新场景下维持缓存正确性。本文提出Aker，一款面向基于磁盘的ANNS的近似缓存。Aker通过两项核心设计选择解决上述局限：其一，引入单查询相似度阈值，每个缓存条目维护自身阈值，该阈值会根据观测到的缓存命中模式动态调整，此设计使Aker能够适配邻域密度，从而兼顾效率与准确率；其二，提出del-consistency，一种面向ANNS缓存的一致性模型，该模型采用删除操作立即执行、插入操作延迟执行的策略，基于此模型，Aker实现了低开销的刷新机制，可限制缓存陈旧度并保持高搜索准确率。我们将Aker集成至pgvector中，并在代表性工作负载上对其进行评估。相较于现有方案，Aker的召回率最高提升64个百分点，查询每秒处理数（QPS）最高提升3.2倍，同时仅使用pgvector共享缓冲区0.6倍的内存。
英文摘要：
Disk-based approximate nearest neighbor search (ANNS) incurs high I/O overhead due to frequent disk accesses during index traversal. Approximate caching, which reuses the results of past queries to serve future similar queries, offers a promising approach to bypass expensive disk searches. However, existing approaches suffer from two key limitations. First, their approximate hit predicates fail to simultaneously achieve high throughput and high accuracy, as they do not adapt to the varying local neighbor density in high-dimensional spaces. Second, they lack an effective refresh mechanism to maintain cache correctness under vector updates. We present Aker, an approximate cache for disk-based ANNS. Aker addresses these limitations through two core design choices. First, we introduce a per-query similarity threshold, where each cache entry maintains its own threshold that is dynamically adjusted based on observed cache hit patterns. This design enables Aker to adapt to neighborhood densities to preserve both efficiency and accuracy. Second, we propose del-consistency, a consistency model for ANNS caches that applies deletions eagerly and insertions lazily. Under this model, Aker implements a low-overhead refresh mechanism that bounds cache staleness and preserves high search accuracy. We integrate Aker into pgvector and evaluate it on representative workloads. Aker improves recall by up to 64 percentage points over prior solutions and increases QPS by up to 3.2x, while using 0.6x the memory of pgvector's shared buffers.
