Local Orthogonal Decomposition for Maximum Inner Product Search

03/25/2019
by   Xiang Wu, et al.
8

Inverted file and asymmetric distance computation (IVFADC) have been successfully applied to approximate nearest neighbor search and subsequently maximum inner product search. In such a framework, vector quantization is used for coarse partitioning while product quantization is used for quantizing residuals. In the original IVFADC as well as all of its variants, after residuals are computed, the second production quantization step is completely independent of the first vector quantization step. In this work, we seek to exploit the connection between these two steps when we perform non-exhaustive search. More specifically, we decompose a residual vector locally into two orthogonal components and perform uniform quantization and multiscale quantization to each component respectively. The proposed method, called local orthogonal decomposition, combined with multiscale quantization consistently achieves higher recall than previous methods under the same bitrates. We conduct comprehensive experiments on large scale datasets as well as detailed ablation tests, demonstrating effectiveness of our method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/03/2021

Projective Clustering Product Quantization

This paper suggests the use of projective clustering based product quant...
research
12/04/2017

Composite Quantization

This paper studies the compact coding approach to approximate nearest ne...
research
08/27/2019

New Loss Functions for Fast Maximum Inner Product Search

Quantization based methods are popular for solving large scale maximum i...
research
04/16/2021

Search-oriented Differentiable Product Quantization

Product quantization (PQ) is a popular approach for maximum inner produc...
research
03/09/2022

Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes

Product quantization (PQ) coupled with a space rotation, is widely used ...
research
09/07/2016

Polysemous codes

This paper considers the problem of approximate nearest neighbor search ...
research
11/29/2017

Online Product Quantization

Approximate nearest neighbor (ANN) search has achieved great success in ...

Please sign up or login with your details

Forgot password? Click here to reset