English

RNSG: A Range-Aware Graph Index for Efficient Range-Filtered Approximate Nearest Neighbor Search

Databases 2026-05-05 v2

Abstract

Range-filtered approximate nearest neighbor (RFANN) search is a fundamental operation in modern data systems. Given a set of objects, each with a vector and a numerical attribute, an RFANN query retrieves the nearest neighbors to a query vector among those objects whose numerical attributes fall within the range specified by the query. Existing state-of-the-art methods for RFANN search often require constructing multiple range-specific graph indexes to achieve high query performance, which incurs significant indexing overhead. To address this, we first establish a novel graph indexing theory, the range-aware relative neighborhood graph (RRNG), which jointly considers spatial and attribute proximity. We prove that the RRNG satisfies two crucial properties: (1) monotonic search-ability, which ensures correct nearest neighbor retrieval via beam search; and (2) structural heredity, which guarantees that any range-induced subgraph remains a valid RRNG, thus enabling efficient search with a single graph index. Based on this theoretical foundation, we propose a new graph index called RNSG as a practical solution that efficiently approximates RRNG. We develop fast algorithms for both constructing the RNSG index and processing RFANN queries with it. Extensive experiments on five real-world datasets show that RNSG achieves significantly higher query performance with a more compact index and lower construction cost than existing state-of-the-art methods.

Keywords

Cite

@article{arxiv.2603.12913,
  title  = {RNSG: A Range-Aware Graph Index for Efficient Range-Filtered Approximate Nearest Neighbor Search},
  author = {Zhiqiu Zou and Ziqi Yin and Rong-Hua Li and Hongchao Qin and Qiangqiang Dai and Guoren Wang},
  journal= {arXiv preprint arXiv:2603.12913},
  year   = {2026}
}

Comments

16 pages, 12 figures. Full version with appendix. Submitted to PVLDB Volume 19 (VLDB 2026), under review

R2 v1 2026-07-01T11:18:18.537Z