LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jääsaari, Elias, Hyvönen, Ville, Roos, Teemu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914987327356928
author Jääsaari, Elias
Hyvönen, Ville
Roos, Teemu
author_facet Jääsaari, Elias
Hyvönen, Ville
Roos, Teemu
contents Approximate nearest neighbor (ANN) search is a key component in many modern machine learning pipelines; recent use cases include retrieval-augmented generation (RAG) and vector databases. Clustering-based ANN algorithms, that use score computation methods based on product quantization (PQ), are often used in industrial-scale applications due to their scalability and suitability for distributed and disk-based implementations. However, they have slower query times than the leading graph-based ANN algorithms. In this work, we propose a new supervised score computation method based on the observation that inner product approximation is a multivariate (multi-output) regression problem that can be solved efficiently by reduced-rank regression. Our experiments show that on modern high-dimensional data sets, the proposed reduced-rank regression (RRR) method is superior to PQ in both query latency and memory usage. We also introduce LoRANN, a clustering-based ANN library that leverages the proposed score computation method. LoRANN is competitive with the leading graph-based algorithms and outperforms the state-of-the-art GPU ANN methods on high-dimensional data sets.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18926
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
Jääsaari, Elias
Hyvönen, Ville
Roos, Teemu
Machine Learning
Approximate nearest neighbor (ANN) search is a key component in many modern machine learning pipelines; recent use cases include retrieval-augmented generation (RAG) and vector databases. Clustering-based ANN algorithms, that use score computation methods based on product quantization (PQ), are often used in industrial-scale applications due to their scalability and suitability for distributed and disk-based implementations. However, they have slower query times than the leading graph-based ANN algorithms. In this work, we propose a new supervised score computation method based on the observation that inner product approximation is a multivariate (multi-output) regression problem that can be solved efficiently by reduced-rank regression. Our experiments show that on modern high-dimensional data sets, the proposed reduced-rank regression (RRR) method is superior to PQ in both query latency and memory usage. We also introduce LoRANN, a clustering-based ANN library that leverages the proposed score computation method. LoRANN is competitive with the leading graph-based algorithms and outperforms the state-of-the-art GPU ANN methods on high-dimensional data sets.
title LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
topic Machine Learning
url https://arxiv.org/abs/2410.18926