MINT: Multi-Vector Search Index Tuning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Jiongli, Wang, Yue, Ding, Bailu, Bernstein, Philip A., Narasayya, Vivek, Chaudhuri, Surajit
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910186135879680
author Zhu, Jiongli
Wang, Yue
Ding, Bailu
Bernstein, Philip A.
Narasayya, Vivek
Chaudhuri, Surajit
author_facet Zhu, Jiongli
Wang, Yue
Ding, Bailu
Bernstein, Philip A.
Narasayya, Vivek
Chaudhuri, Surajit
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2504_20018
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MINT: Multi-Vector Search Index Tuning
Zhu, Jiongli
Wang, Yue
Ding, Bailu
Bernstein, Philip A.
Narasayya, Vivek
Chaudhuri, Surajit
Databases
Artificial Intelligence
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.
title MINT: Multi-Vector Search Index Tuning
topic Databases
Artificial Intelligence
url https://arxiv.org/abs/2504.20018