EUVIMEDEUVIMED entdecken
Crossref

Harmonizing Efficiency and Accuracy in Filtered Vector Search

Zixiang Zhou, Xuhao Chen

Proceedings of the VLDB Endowment · 01.05.2026 · 19 (9) · 2059-2072

DOI: 10.14778/3819518.3819534 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 19.08.2026. Verfasst von Zixiang Zhou und 1 weiteren Autor:innen. Die Arbeit nennt 74 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Approximate nearest neighbor search (ANNS) is increasingly essential for AI-driven applications. In practice, ANNS is often coupled with label filtering to improve accuracy, relevance, and efficiency, a variant known as filtered ANNS or FANNS. Existing FANNS methods fall short in efficiency or accuracy. This is because, first, searching on a label-mixed index often converges to local minima due to label interference. Second, isolating and duplicating labels in the index inflates the index and incurs prohibitive memory overhead. Third, current join-based strategies for multi-filter search perform substantial wasted computation on unpromising candidates. We present BigFANN, a label-aware FANNS framework that achieves high speed and space efficiency, while retaining high accuracy. Our framework features a hybrid indexing scheme that introduces heterogeneous edge types and flexible IVF-graph indexing. Specifically, we construct graph indices with tunable combinations of exclusive and shared edges based on label characteristics. This method effectively minimizes label interference for single-filter search under a certain memory budget, ensuring high search accuracy and speed. In addition to heterogeneous edges, we adopt a hybrid of graph and IVF indices to deal with single- and multi-filter queries. Particularly, for multi-filter searches, we propose a join-free search strategy to eliminate wasted computation in the existing join-based strategy. Experimental results on various datasets show that BigFANN significantly outperforms state-of-the-art FANNS frameworks, UNG and ParlayIVF 2 , by up to 786× and 4× respectively, while achieving the same or better accuracy.

Zitieren

APA

Zhou, Z., & Chen, X. (2026). Harmonizing Efficiency and Accuracy in Filtered Vector Search. Proceedings of the VLDB Endowment, 19(9), 2059-2072. https://doi.org/10.14778/3819518.3819534

Vancouver

Zhou Z, Chen X. Harmonizing Efficiency and Accuracy in Filtered Vector Search. Proceedings of the VLDB Endowment. 2026;19(9):2059-2072. doi:10.14778/3819518.3819534

BibTeX
@article{Zhou2026,
  author = {Zhou, Zixiang and Chen, Xuhao},
  title = {Harmonizing Efficiency and Accuracy in Filtered Vector Search},
  journal = {Proceedings of the VLDB Endowment},
  year = {2026},
  volume = {19},
  number = {9},
  pages = {2059--2072},
  doi = {10.14778/3819518.3819534}
}
Kostenlos starten →