Accelerating Large-Scale Inference with Anisotropic Vector Quantization

TL;DR

This paper introduces anisotropic vector quantization techniques that improve large-scale inner product search by focusing on query-relevant data points, achieving state-of-the-art results in benchmark tests.

Contribution

It proposes a novel anisotropic quantization loss that emphasizes relevant components, enhancing the efficiency of maximum inner product search in large databases.

Findings

Achieves state-of-the-art results on public benchmarks.

Develops a new variant of vector quantization.

Focuses on query-relevant data points for improved accuracy.

Abstract

Quantization based techniques are the current state-of-the-art for scaling maximum inner product search to massive databases. Traditional approaches to quantization aim to minimize the reconstruction error of the database points. Based on the observation that for a given query, the database points that have the largest inner products are more relevant, we develop a family of anisotropic quantization loss functions. Under natural statistical assumptions, we show that quantization with these loss functions leads to a new variant of vector quantization that more greatly penalizes the parallel component of a datapoint's residual relative to its orthogonal component. The proposed approach achieves state-of-the-art results on the public benchmarks available at \url{ann-benchmarks.com}.