BoomHQ: Learning to Boost Multiple Hybrid Queries on Vector DBMSs

2026-04-27

AI Summary

This work addresses the inefficiency of existing vector databases in handling multi-vector hybrid queries with complex scalar predicates, primarily due to their inability to exploit correlations between vector and scalar attributes and the selectivity distribution of query neighborhoods. To overcome this limitation, we propose BoomHQ—the first learning-based optimization framework that jointly models vector-scalar correlations and neighborhood selectivity. BoomHQ employs an autoencoder to capture attribute dependencies and leverages query pattern analysis to generate execution hints and rewrite queries accordingly. Supporting multiple vector columns and complex predicates, our approach demonstrates strong adaptability to data updates and generalizes effectively across systems. Evaluated on three major vector databases, BoomHQ achieves consistent performance gains, delivering an average 2× speedup over state-of-the-art methods while preserving recall, with peak improvements exceeding 25×.

Technology Category

• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Intelligent Query Processing
• Intelligent Robots: Learning & Optimization for ROB

Application Category

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

Abstract

Hybrid queries, which combine vector nearest neighbor searches with scalar predicates, represent a fundamental challenge in managing vector databases. Existing methods often restrict the number of vector columns involved or the complexity of scalar predicates, thereby limiting their flexibility in handling diverse query patterns. Moreover, these approaches typically do not fully leverage the correlations between scalar and vector attributes, or the distributional patterns observed from query vector neighborhoods. To address these limitations, we introduce BoomHQ, a learning-based framework to boost multiple hybrid queries on vector DBMSs. First, BoomHQ models the correlation between vector and scalar attributes using an autoencoder-based architecture, which is also friendly to data updates. Second, BoomHQ captures prevailing query patterns, particularly using estimated selectivity of scalar predicates within the neighborhood of a query vector. Guided by these two key features, BoomHQ predicts the execution hints and rewrites the original query into an optimized version. Furthermore, we extend well-known benchmarks by introducing vector and scalar data with inherent correlations to better evaluate query execution. Experimental results demonstrate that for multiple hybrid queries at specified recall thresholds, our method achieves a 2x average and over 25x peak speedup compared to the state-of-the-art. Additionally, BoomHQ shows strong robustness against data updates and consistent optimization effectiveness across three representative vector database systems.

Problem

• hybrid queries
• vector databases
• scalar predicates
• query optimization
• vector-scalar correlation

Innovation

• hybrid query optimization
• vector-scalar correlation
• learning-based query rewriting
• autoencoder architecture
• selectivity estimation