STABLE: Efficient Hybrid Nearest Neighbor Search via Magnitude-Uniformity and Cardinality-Robustness

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Yang, Qianyun, Chen, Zhiwei, Hu, Yupeng, Li, Zixu, Fu, Zhiheng, Nie, Liqiang
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Information Retrieval
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

_version_	1866918425328091136
author	Yang, Qianyun Chen, Zhiwei Hu, Yupeng Li, Zixu Fu, Zhiheng Nie, Liqiang
author_facet	Yang, Qianyun Chen, Zhiwei Hu, Yupeng Li, Zixu Fu, Zhiheng Nie, Liqiang
contents	Hybrid Approximate Nearest Neighbor Search (Hybrid ANNS) is a foundational search technology for large-scale heterogeneous data and has gained significant attention in both academia and industry. However, current approaches overlook the heterogeneity in data distribution, thus ignoring two major challenges: the Compatibility Barrier for Similarity Magnitude Heterogeneity and the Tolerance Bottleneck to Attribute Cardinality. To overcome these issues, we propose the robuSt heTerogeneity-Aware hyBrid retrievaL framEwork, STABLE, designed for accurate, efficient, and robust hybrid ANNS under datasets with various distributions. Specifically, we introduce an enhAnced heterogeneoUs semanTic perceptiOn (AUTO) metric to achieve a joint measurement of feature similarity and attribute consistency, addressing similarity magnitude heterogeneity and improving robustness to datasets with various attribute cardinalities. Thereafter, we construct our Heterogeneous sEmantic reLation graPh (HELP) index based on AUTO to organize heterogeneous semantic relations. Finally, we employ a novel Dynamic Heterogeneity Routing method to ensure an efficient search. Extensive experiments on five feature vector benchmarks with various attribute cardinalities demonstrate the superior performance of STABLE.
format	Preprint
id	arxiv_https___arxiv_org_abs_2604_01617
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	STABLE: Efficient Hybrid Nearest Neighbor Search via Magnitude-Uniformity and Cardinality-Robustness Yang, Qianyun Chen, Zhiwei Hu, Yupeng Li, Zixu Fu, Zhiheng Nie, Liqiang Information Retrieval Hybrid Approximate Nearest Neighbor Search (Hybrid ANNS) is a foundational search technology for large-scale heterogeneous data and has gained significant attention in both academia and industry. However, current approaches overlook the heterogeneity in data distribution, thus ignoring two major challenges: the Compatibility Barrier for Similarity Magnitude Heterogeneity and the Tolerance Bottleneck to Attribute Cardinality. To overcome these issues, we propose the robuSt heTerogeneity-Aware hyBrid retrievaL framEwork, STABLE, designed for accurate, efficient, and robust hybrid ANNS under datasets with various distributions. Specifically, we introduce an enhAnced heterogeneoUs semanTic perceptiOn (AUTO) metric to achieve a joint measurement of feature similarity and attribute consistency, addressing similarity magnitude heterogeneity and improving robustness to datasets with various attribute cardinalities. Thereafter, we construct our Heterogeneous sEmantic reLation graPh (HELP) index based on AUTO to organize heterogeneous semantic relations. Finally, we employ a novel Dynamic Heterogeneity Routing method to ensure an efficient search. Extensive experiments on five feature vector benchmarks with various attribute cardinalities demonstrate the superior performance of STABLE.
title	STABLE: Efficient Hybrid Nearest Neighbor Search via Magnitude-Uniformity and Cardinality-Robustness
topic	Information Retrieval
url	https://arxiv.org/abs/2604.01617