JAG: Joint Attribute Graphs for Filtered Nearest Neighbor Search

2026-02-10

AI Summary

Existing filtered nearest neighbor search methods exhibit unstable performance and limited generalization across varying query selectivities and filter types. This work proposes a graph-based joint attribute graph approach that transforms binary filtering constraints into continuous navigation signals by incorporating attribute distance and filter distance, thereby effectively mitigating dead-end issues during graph traversal. The method constructs a jointly optimized proximity graph that integrates vector embeddings with attribute information, enabling unified support for diverse filter types—including label, range, subset, and Boolean queries. Extensive experiments across five datasets and four filter categories demonstrate that the proposed approach significantly outperforms state-of-the-art methods in both throughput and recall stability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Distributed Search
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• filtered nearest neighbor search
• query selectivity
• filter type
• vector search
• generalization

Innovation

• Joint Attribute Graphs
• Filtered Nearest Neighbor Search
• Attribute Distance
• Filter Distance
• Proximity Graph