AQR-HNSW：通过密度感知量化和多阶段重排序加速近似最近邻搜索
AQR-HNSW: Accelerating Approximate Nearest Neighbor Search via Density-aware Quantization and Multi-stage Re-ranking
AI总结：
AQR-HNSW通过密度感知量化和多阶段重排序提升HNSW算法的可扩展性，实现更高的查询速度和更低的内存消耗。
摘要：
近似最近邻（ANN）搜索已成为现代AI基础设施的核心，驱动着推荐系统、搜索引擎和大型语言模型，从谷歌到OpenAI等行业领导者均广泛应用。分层可导航小世界（HNSW）图已发展为主导的ANN算法，因其在召回率与延迟之间的平衡优势，被广泛应用于生产系统。然而，随着向量数据库扩展到数十亿个嵌入，HNSW面临关键瓶颈：内存消耗增加，距离计算开销主导查询延迟，并在异构数据分布上表现不佳。本文提出了自适应量化和重排序HNSW（AQR-HNSW），一种新型框架，通过整合三种策略来提升HNSW的可扩展性。AQR-HNSW引入（1）密度感知自适应量化，实现4倍压缩同时保持距离关系；（2）多阶段重排序，通过减少35%的不必要的计算；以及（3）量化优化的SIMD实现，跨架构实现每周期16-64次操作。在标准基准上的评估显示，AQR-HNSW比最先进的HNSW实现每秒查询数（QPS）高2.5-3.3倍，同时保持超过98%的召回率，索引图内存减少75%，索引构建速度提升5倍。
英文摘要：
Approximate Nearest Neighbor (ANN) search has become fundamental to modern AI infrastructure, powering recommendation systems, search engines, and large language models across industry leaders from Google to OpenAI. Hierarchical Navigable Small World (HNSW) graphs have emerged as the dominant ANN algorithm, widely adopted in production systems due to their superior recall versus latency balance. However, as vector databases scale to billions of embeddings, HNSW faces critical bottlenecks: memory consumption expands, distance computation overhead dominates query latency, and it suffers suboptimal performance on heterogeneous data distributions. This paper presents Adaptive Quantization and Rerank HNSW (AQR-HNSW), a novel framework that synergistically integrates three strategies to enhance HNSW scalability. AQR-HNSW introduces (1) density-aware adaptive quantization, achieving 4x compression while preserving distance relationships; (2) multi-state re-ranking that reduces unnecessary computations by 35%; and (3) quantization-optimized SIMD implementations delivering 16-64 operations per cycle across architectures. Evaluation on standard benchmarks demonstrates 2.5-3.3x higher queries per second (QPS) than state-of-the-art HNSW implementations while maintaining over 98% recall, with 75% memory reduction for the index graph and 5x faster index construction.
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。
