FAVOR: Efficient Filter-Agnostic Vector ANNS Based on Selectivity-Aware Exclusion Distances

TL;DR

FAVOR is a novel filter-agnostic vector approximate nearest neighbor search method that efficiently handles complex attribute filtering and varying selectivity levels, improving throughput and maintaining high recall.

Contribution

It introduces an integrated architecture, a dynamic exclusion distance mechanism, and a selectivity-driven search routing strategy for hybrid vector-attribute queries.

Findings

FAVOR achieves 1.3-5× higher QPS at 95% recall compared to state-of-the-art methods.

It maintains stable performance across different filtering selectivity levels.

The method effectively balances search efficiency, filtering generality, and index connectivity.

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$\times$ 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.