Efficient Approximate Nearest Neighbor Search under Multi-Attribute Range Filter

2026-02-17

AI Summary

This work addresses the challenge of efficiently supporting multi-attribute numeric range constraints in high-dimensional nearest neighbor search. To this end, the authors propose KHI, a novel index structure that, for the first time, enables effective support for range-filtered k-nearest neighbor queries with multiple attributes. KHI integrates a hierarchical partitioning tree over the attribute space with Hierarchical Navigable Small World (HNSW) graphs embedded within each node. It employs a skew-aware splitting strategy to control tree height and performs greedy HNSW search along tree paths. Experimental evaluation on four real-world datasets demonstrates that KHI achieves an average throughput improvement of 2.46× over the state-of-the-art method, with gains reaching up to 16.22×, particularly excelling under low selectivity, large k values, and high predicate cardinality scenarios.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Search and Optimization: Distributed Search
• Machine Learning: Kernel Methods

Application Category

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

Abstract

Nearest neighbor search on high-dimensional vectors is fundamental in modern AI and database systems. In many real-world applications, queries involve constraints on multiple numeric attributes, giving rise to range-filtering approximate nearest neighbor search (RFANNS). While there exist RFANNS indexes for single-attribute range predicates, extending them to the multi-attribute setting is nontrivial and often ineffective. In this paper, we propose KHI, an index for multi-attribute RFANNS that combines an attribute-space partitioning tree with HNSW graphs attached to tree nodes. A skew-aware splitting rule bounds the tree height by $O(\log n)$, and queries are answered by routing through the tree and running greedy search on the HNSW graphs. Experiments on four real-world datasets show that KHI consistently achieves high query throughput while maintaining high recall. Compared with the state-of-the-art RFANNS baseline, KHI improves QPS by $2.46\times$ on average and up to $16.22\times$ on the hard dataset, with larger gains for smaller selectivity, larger $k$, and higher predicate cardinality.

Problem

• Approximate Nearest Neighbor Search
• Multi-Attribute Range Filter
• High-Dimensional Vectors
• Range Filtering
• RFANNS

Innovation

• multi-attribute range filtering
• approximate nearest neighbor search
• HNSW graph
• skew-aware partitioning
• KHI index