Key points are not available for this paper at this time.
Filtered approximate nearest neighbor (ANN) search over high-dimensional vectors and associated attributes is critical for recommendation systems and RAG-based LLMs. However, existing methods face performance bottlenecks under workloads of varying characteristics due to static and single neighbor-handling strategies---either computing distances before filtering or filtering before distance computation---which fail to adapt to diverse data and workload patterns. In this paper, we propose PathSeer, an approach that enables efficient filtered ANN search through dynamic and hybrid neighbor-handling strategies. PathSeer introduces three key techniques: (1) a fusion vector indexing scheme that supports two neighbor-handling strategies within a single index, (2) a dynamic neighbor traversal strategy that allows adjusting the ratios of different neighbor-handling strategies at each step of index traversal while preserving high search performance, and (3) a heuristic parameter tuning mechanism that adapts the ratios of neighbors employing different neighbor-handling strategies to workload characteristics. Evaluations on six workloads show that PathSeer delivers 1.17×–47.4× higher throughput for filtered ANN search compared to existing methods, without sacrificing recall.
Building similarity graph...
Analyzing shared references across papers
Loading...
Zhiyue Li
Guangyan Zhang
Ruochun Jin
Proceedings of the ACM on Management of Data
Tsinghua University
National University of Defense Technology
Building similarity graph...
Analyzing shared references across papers
Loading...
Li et al. (Mon,) studied this question.
www.synapsesocial.com/papers/6a0d4ee2f03e14405aa9a122 — DOI: https://doi.org/10.1145/3802098
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: