FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances
Proceedings of the ACM on Management of Data · 18.05.2026 · 4 (3) · 1-25
DOI: 10.1145/3802060 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 18.05.2026. Verfasst von Junjie Song und 6 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Gefördert von: National Key Research and Development Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
Modern retrieval systems increasingly require integrating approximate nearest neighbor search (ANNS) with complex attribute filtering to handle hybrid queries in applications such as recommendation systems and retrieval-augmented generation (RAG). While HNSW-based inline-filtering methods show promise, existing approaches struggle to deliver high throughput under low-selectivity scenarios while balancing search efficiency, filtering generality, and index connectivity. To address these challenges, we propose FAVOR, an efficient filter-agnostic vector ANNS that supports arbitrary filtering conditions while maintaining stable performance across varying selectivity levels. FAVOR introduces three novel features: (1) an integrated architecture that unifies selectivity estimation and filtered ANNS execution, providing a cohesive solution for hybrid vector–attribute queries; (2) a HNSW-based inline-filtering algorithm that introduces an exclusion distance mechanism to dynamically reshape the vector distance distribution, pushing non-target vectors away from the query while promoting valid candidates toward the query, thus improving search efficiency without compromising generality or graph connectivity; and (3) a selectivity-driven search selector that estimates query selectivity and dynamically routes queries between a pre-filtering brute-force algorithm for low-selectivity cases and an optimized HNSW-based search algorithm for other scenarios, ensuring consistent performance. Extensive experiments on real-world datasets demonstrate that FAVOR achieves a 1.3–5× higher QPS at Recall@10 = 95% compared to state-of-the-art methods for arbitrary filtering conditions, while maintaining competitive performance even against tailored solutions in some filtering conditions.
Förderung
- National Key Research and Development Program
- National Natural Science Foundation of China
Zitieren
APA
Song, J., Liu, Y., Hu, G., Xie, Z., Yang, M., Ooi, B. C., & Zhou, K. (2026). FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances. Proceedings of the ACM on Management of Data, 4(3), 1-25. https://doi.org/10.1145/3802060
Vancouver
Song J, Liu Y, Hu G, Xie Z, Yang M, Ooi BC, et al. FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances. Proceedings of the ACM on Management of Data. 2026;4(3):1-25. doi:10.1145/3802060
BibTeX
@article{Song2026,
author = {Song, Junjie and Liu, Yu and Hu, Guoyu and Xie, Zhongle and Yang, Ming and Ooi, Beng Chin and Zhou, Ke},
title = {FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances},
journal = {Proceedings of the ACM on Management of Data},
year = {2026},
volume = {4},
number = {3},
pages = {1--25},
doi = {10.1145/3802060}
}
EUVIMED