Jointly Optimizing Query Encoder And Product Quantization To Improve Retrieval Performance
2021 · Jingtao Zhan, Jiaxin Mao, Yiqun Liu, et al.
Abstract
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 thre
Authors
(none)
Tags
Stats
Related papers
- Matching-oriented Product Quantization For Ad-hoc Retrieval (2021)2.29
- Joint Learning Of Deep Retrieval Model And Product Quantization Based Embedding Index (2021)10.35
- Beyond Product Quantization: Deep Progressive Quantization For Image Retrieval (2019)12.95
- End-to-end Supervised Product Quantization For Image Search And Retrieval (2017)13.05
- Pqtable: Non-exhaustive Fast Search For Product-quantized Codes Using Hash Tables (2017)7.16
- Learning Discrete Representations Via Constrained Clustering For Effective And Efficient Dense Retrieval (2021)11.39
- Distill-vq: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge From Dense Embeddings (2022)0.00
- Aisaq: All-in-storage ANNS With Product Quantization For Dram-free Information Retrieval (2024)0.00