Efficient and Effective Retrieval of Dense-Sparse Hybrid Vectors using Graph-based Approximate Nearest Neighbor Search

TL;DR

This paper introduces a graph-based approximate nearest neighbor search algorithm for dense-sparse hybrid vectors, improving accuracy and efficiency with a novel distribution alignment and adaptive computation strategy, significantly outperforming existing methods.

Contribution

It presents a unified graph-based ANNS method for hybrid vectors, incorporating a distribution alignment for accuracy and a two-stage adaptive strategy for efficiency, addressing scalability and complexity issues.

Findings

Achieves 1%-9% accuracy improvement with distribution alignment.

Provides approximately 2.1x speedup over naive implementations.

Attains 8.9x-11.7x throughput at equal accuracy compared to existing methods.

Abstract

ANNS for embedded vector representations of texts is commonly used in information retrieval, with two important information representations being sparse and dense vectors. While it has been shown that combining these representations improves accuracy, the current method of conducting sparse and dense vector searches separately suffers from low scalability and high system complexity. Alternatively, building a unified index faces challenges with accuracy and efficiency. To address these issues, we propose a graph-based ANNS algorithm for dense-sparse hybrid vectors. Firstly, we propose a distribution alignment method to improve accuracy, which pre-samples dense and sparse vectors to analyze their distance distribution statistic, resulting in a 1%$\sim$9% increase in accuracy. Secondly, to improve efficiency, we design an adaptive two-stage computation strategy that initially computes dense distances only and later computes hybrid distances. Further, we prune the sparse vectors to speed up the calculation. Compared to naive implementation, we achieve $\sim2.1\times$ acceleration. Thorough experiments show that our algorithm achieves 8.9x$\sim$11.7x throughput at equal accuracy compared to existing hybrid vector search algorithms.