Joint Learning of Deep Retrieval Model and Product Quantization based Embedding Index

Abstract

Embedding index that enables fast approximate nearest neighbor(ANN) search, serves as an indispensable component for state-of-the-art deep retrieval systems. Traditional approaches, often separating the two steps of embedding learning and index building, incur additional indexing time and decayed retrieval accuracy. In this paper, we propose a novel method called Poeem, which stands for product quantization based embedding index jointly trained with deep retrieval model, to unify the two separate steps within an end-to-end training, by utilizing a few techniques including the gradient straight-through estimator, warm start strategy, optimal space decomposition and Givens rotation. Extensive experimental results show that the proposed method not only improves retrieval accuracy significantly but also reduces the indexing time to almost none. We have open sourced our approach for the sake of comparison and reproducibility.

4 pages, 4 figures; accepted by SIGIR2021

References in corpus (2)

• Learning Tree-based Deep Model for Recommender Systems
• Embedding-based Retrieval in Facebook Search

Cited by in corpus (6)

• Information Retrieval: Recent Advances and Beyond
• Lexically-Accelerated Dense Retrieval
• Adaptive In-Context Learning with Large Language Models for Bundle Generation
• Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval
• Differentiable Retrieval Augmentation via Generative Language Modeling for E-commerce Query Intent Classification
• Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search