DBAIApr 28, 2025

MINT: Multi-Vector Search Index Tuning

arXiv:2504.20018v1h-index: 41
Originality Incremental advance
AI Analysis

This addresses performance optimization for multi-ector search in applications like multi-modal and multi-feature scenarios, representing an incremental advancement in database tuning.

The paper tackles the problem of index tuning for multi-vector search in databases, proposing a framework that achieves a 2.1X to 8.3X speedup in latency compared to a baseline.

Vector search plays a crucial role in many real-world applications. In addition to single-vector search, multi-vector search becomes important for multi-modal and multi-feature scenarios today. In a multi-vector database, each row is an item, each column represents a feature of items, and each cell is a high-dimensional vector. In multi-vector databases, the choice of indexes can have a significant impact on performance. Although index tuning for relational databases has been extensively studied, index tuning for multi-vector search remains unclear and challenging. In this paper, we define multi-vector search index tuning and propose a framework to solve it. Specifically, given a multi-vector search workload, we develop algorithms to find indexes that minimize latency and meet storage and recall constraints. Compared to the baseline, our latency achieves 2.1X to 8.3X speedup.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes