RaG-Tree: Combining R-Tree and HNSW for Multi-Attribute Range Filtered Approximate Nearest Neighbor Search

2026-08-02

AI Summary

This work addresses the problem of approximate nearest neighbor search under multi-attribute range constraints (MR-ANNS) by proposing RaG-Tree, a unified indexing structure that integrates R-trees with partition-aware, sparsity-adaptive HNSW graphs. RaG-Tree leverages hierarchical attribute-range pruning via R-trees and embeds locally optimized HNSW graphs within each partition to jointly exploit correlations among attributes as well as between attributes and embedding vectors. Coupled with a cost-based adaptive search strategy and an incremental maintenance mechanism, RaG-Tree achieves high query efficiency, lightweight index construction, and dynamic update support. Experimental results on three real-world datasets demonstrate that the proposed method significantly outperforms existing approaches, achieving high recall while substantially improving query performance and scalability.

Abstract

Multi-attribute range-filtered approximate nearest neighbor search (MR-ANNS), which retrieves high-dimensional vectors satisfying multiple attribute constraints, is a fundamental operation in modern AI applications. Existing MR-ANNS indexes either exploit a single attribute for range localization or recursively partition objects along individual attributes, which may limit their ability to exploit attribute correlations for effective range pruning and attribute-vector correlations for efficient nearest-neighbor search. In this paper, we propose RaG-Tree, a unified index that couples an R-tree with partition-aware HNSW graphs for MR-ANNS. RaG-Tree leverages hierarchical R-tree partitions for effective range pruning and adapts the sparsity of each HNSW graph to the local vector distributions within its partition, enabling lightweight indexing and efficient query processing. To support efficient query processing and dynamic updates, we develop a cost-based adaptive search algorithm that minimizes unnecessary graph exploration, together with an efficient index maintenance mechanism for incrementally updating affected partition-aware HNSW graphs. Extensive experiments on three real-world datasets show that RaG-Tree achieves superior query performance over state-of-the-art baselines, while also providing lightweight indexing and fast incremental updates.

Problem

• multi-attribute range filtering
• approximate nearest neighbor search
• attribute correlation
• range pruning
• high-dimensional vectors

Innovation

• RaG-Tree
• multi-attribute range filtering
• approximate nearest neighbor search
• R-tree
• HNSW