JAG: Joint Attribute Graphs for Filtered Nearest Neighbor Search

TL;DR

JAG is a graph-based algorithm that improves filtered nearest neighbor search by supporting diverse filters and query selectivities, outperforming prior methods in robustness and efficiency.

Contribution

JAG introduces attribute and filter distances to create a unified graph structure that handles various filter types and selectivities effectively.

Findings

JAG outperforms existing methods in throughput and recall.

It supports multiple filter types including Label, Range, Subset, Boolean.

Experimental results show robustness across five datasets.

Abstract

Despite filtered nearest neighbor search being a fundamental task in modern vector search systems, the performance of existing algorithms is highly sensitive to query selectivity and filter type. In particular, existing solutions excel either at specific filter categories (e.g., label equality) or within narrow selectivity bands (e.g., pre-filtering for low selectivity) and are therefore a poor fit for practical deployments that demand generalization to new filter types and unknown query selectivities. In this paper, we propose JAG (Joint Attribute Graphs), a graph-based algorithm designed to deliver robust performance across the entire selectivity spectrum and support diverse filter types. Our key innovation is the introduction of attribute and filter distances, which transform binary filter constraints into continuous navigational guidance. By constructing a proximity graph that jointly optimizes for both vector similarity and attribute proximity, JAG prevents navigational dead-ends and allows JAG to consistently outperform prior graph-based filtered nearest neighbor search methods. Our experimental results across five datasets and four filter types (Label, Range, Subset, Boolean) demonstrate that JAG significantly outperforms existing state-of-the-art baselines in both throughput and recall robustness.