EUVIMEDOpdag EUVIMED
Crossref

PathSeer: Adaptive Neighbor Handling for Efficient Filtered ANN Search

Zhiyue Li, Guangyan Zhang, Ruochun Jin, Bojun Li, Xiaoguang Ren, Wenjing Yang

Proceedings of the ACM on Management of Data · 2026-05-18 · 4 (3) · 1-27

DOI: 10.1145/3802098 ↗

At a glance

Journal article in Proceedings of the ACM on Management of Data, published online on 2026-05-18. Written by Zhiyue Li and 5 co-authors. 65 references. Funded by: National Natural Science Foundation of China, Innovation Research Foundation of NUDT, Open Research Fund from State Key Laboratory of High Performance Computing of China.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

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.

Funding

  • National Natural Science Foundation of China
  • Innovation Research Foundation of NUDT
  • Open Research Fund from State Key Laboratory of High Performance Computing of China
  • Young Elite Scientists Sponsorship Program by CAST

Cite

APA

Li, Z., Zhang, G., Jin, R., Li, B., Ren, X., & Yang, W. (2026). PathSeer: Adaptive Neighbor Handling for Efficient Filtered ANN Search. Proceedings of the ACM on Management of Data, 4(3), 1-27. https://doi.org/10.1145/3802098

Vancouver

Li Z, Zhang G, Jin R, Li B, Ren X, Yang W. PathSeer: Adaptive Neighbor Handling for Efficient Filtered ANN Search. Proceedings of the ACM on Management of Data. 2026;4(3):1-27. doi:10.1145/3802098

BibTeX
@article{Li2026,
  author = {Li, Zhiyue and Zhang, Guangyan and Jin, Ruochun and Li, Bojun and Ren, Xiaoguang and Yang, Wenjing},
  title = {PathSeer: Adaptive Neighbor Handling for Efficient Filtered ANN Search},
  journal = {Proceedings of the ACM on Management of Data},
  year = {2026},
  volume = {4},
  number = {3},
  pages = {1--27},
  doi = {10.1145/3802098}
}
Start for free →