解决异构数据检索中的相似度与属性数量不一致问题，提升搜索精度与效率。
STABLE: Efficient Hybrid Nearest Neighbor Search via Magnitude-Uniformity and Cardinality-Robustness
- 提出AUTO度量，联合捕捉特征相似性与属性一致性。
- 构建HELP索引图，有效组织异构语义关系。
- 动态路由机制实现高效混合检索，适配多类数据集。
混合近似最近邻搜索（Hybrid ANNS）是大规模异构数据的基础搜索技术，在学术界和工业界均受到广泛关注。然而，现有方法忽略了数据分布的异质性，忽视了两个主要挑战：相似度幅度异质性的兼容性障碍，以及对属性基数的容忍度瓶颈。为此，我们提出robust St hetereogeneity-Aware hyBrid retrievaL框架（STABLE），旨在在多种数据分布下实现准确、高效且鲁棒的混合近似最近邻搜索。具体而言，我们引入增强型异构语义感知（AUTO）度量，实现特征相似性与属性一致性的联合度量，解决了相似度幅度异质性问题，并提升了对不同属性基数数据集的鲁棒性。随后，基于AUTO构建异构语义关系图（HELP）索引，以组织异构语义关系。最后，采用新型动态异质性路由方法确保高效搜索。在五个具有不同属性基数的特征向量基准上的大量实验表明，STABLE表现出优越性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。