Quantization Meets Projection: A Happy Marriage for Approximate k-Nearest Neighbor Search
Summary: MRQ combines projection with dimension-wise quantization, encoding only information-dense leading projected dimensions and summarizing the tail. This decouples code length from original dimensionality, enabling tunable compression and up to 3× faster AKNN search at comparable accuracy. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Mingyu Yang (Hong Kong University of Science and Technology)
- 2. Liuchang Jing (Hong Kong University of Science and Technology)
- 3. Wentao Li (University of Leicester)
- 4. Wei Wang (Hong Kong University of Science and Technology)
BibTeX Citation
@article{yang_vldb26,
title = {{Quantization Meets Projection: A Happy Marriage for Approximate k-Nearest Neighbor Search}},
author = {Yang, Mingyu and Jing, Liuchang and Li, Wentao and Wang, Wei},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {6},
pages = {1240--1249},
doi = {10.14778/3797919.3797931},
url = {https://doi.org/10.14778/3797919.3797931},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 32 of 32 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next