FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances
Open Access
- 18 May 2026
- journal article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (3) , 1-25
Abstract
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.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2023YFB4502701)
- National Natural Science Foundation of China (62232007)
This publication has 32 references indexed in Scilit:
- LAN: Learning-based Approximate k-Nearest Neighbor Search in Graph Databases2022
- Milvus2021
- word2vec, node2vec, graph2vec, X2vec: Towards a Theory of Vector Embeddings of Structured Data2020
- The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform2018
- Optimal Data-Dependent Hashing for Approximate Near Neighbors2015
- Approximate nearest neighbor algorithm based on navigable small world graphsInformation Systems, 2014
- Rank-Based Similarity Search: Reducing the Dimensional DependenceIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Scalable Nearest Neighbor Algorithms for High Dimensional DataIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Near-optimal hashing algorithms for approximate nearest neighbor in high dimensionsCommunications of the ACM, 2008
- Relative neighborhood graphs and their relativesProceedings of the IEEE, 1992