Interleaved Composite Quantization for High-Dimensional Similarity Search

TL;DR

This paper introduces Interleaved Composite Quantization (ICQ), a novel method that enhances high-dimensional similarity search by reducing quantization error without shortening codes, leading to faster and more accurate approximate nearest neighbor retrieval.

Contribution

ICQ is a new quantization technique that balances speed and accuracy by using partial codes for distance approximation and integrating with existing error reduction methods.

Findings

ICQ achieves faster search with comparable or better accuracy.

Empirical results show strong performance on synthetic and real datasets.

ICQ reduces quantization error while maintaining code length.

Abstract

Similarity search retrieves the nearest neighbors of a query vector from a dataset of high-dimensional vectors. As the size of the dataset grows, the cost of performing the distance computations needed to implement a query can become prohibitive. A method often used to reduce this computational cost is quantization of the vector space and location-based encoding of the dataset vectors. These encodings can be used during query processing to find approximate nearest neighbors of the query point quickly. Search speed can be improved by using shorter codes, but shorter codes have higher quantization error, leading to degraded precision. In this work, we propose the Interleaved Composite Quantization (ICQ) which achieves fast similarity search without using shorter codes. In ICQ, a small subset of the code is used to approximate the distances, with complete codes being used only when necessary. Our method effectively reduces both code length and quantization error. Furthermore, ICQ is compatible with several recently proposed techniques for reducing quantization error and can be used in conjunction with these other techniques to improve results. We confirm these claims and show strong empirical performance of ICQ using several synthetic and real-word datasets.