Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance

08/02/2021
by   Jingtao Zhan, et al.
0

Recently, Information Retrieval community has witnessed fast-paced advances in Dense Retrieval (DR), which performs first-stage retrieval with embedding-based search. Despite the impressive ranking performance, previous studies usually adopt brute-force search to acquire candidates, which is prohibitive in practical Web search scenarios due to its tremendous memory usage and time cost. To overcome these problems, vector compression methods have been adopted in many practical embedding-based retrieval applications. One of the most popular methods is Product Quantization (PQ). However, although existing vector compression methods including PQ can help improve the efficiency of DR, they incur severely decayed retrieval performance due to the separation between encoding and compression. To tackle this problem, we present JPQ, which stands for Joint optimization of query encoding and Product Quantization. It trains the query encoder and PQ index jointly in an end-to-end manner based on three optimization strategies, namely ranking-oriented loss, PQ centroid optimization, and end-to-end negative sampling. We evaluate JPQ on two publicly available retrieval benchmarks. Experimental results show that JPQ significantly outperforms popular vector compression methods. Compared with previous DR models that use brute-force search, JPQ almost matches the best retrieval performance with 30x compression on index size. The compressed index further brings 10x speedup on CPU and 2x speedup on GPU in query latency.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/24/2023

Constructing Tree-based Index for Efficient and Effective Dense Retrieval

Recent studies have shown that Dense Retrieval (DR) techniques can signi...
research
10/12/2021

Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval

Dense Retrieval (DR) has achieved state-of-the-art first-stage ranking e...
research
04/16/2021

Optimizing Dense Retrieval Model Training with Hard Negatives

Ranking has always been one of the top concerns in information retrieval...
research
07/12/2020

Deep Retrieval: An End-to-End Learnable Structure Model for Large-Scale Recommendations

One of the core problems in large-scale recommendations is to retrieve t...
research
05/09/2021

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

Embedding index that enables fast approximate nearest neighbor(ANN) sear...
research
04/14/2021

Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling

A vital step towards the widespread adoption of neural retrieval models ...
research
04/16/2021

Search-oriented Differentiable Product Quantization

Product quantization (PQ) is a popular approach for maximum inner produc...

Please sign up or login with your details

Forgot password? Click here to reset