Efficient Data-aware Distance Comparison Operations for High-Dimensional Approximate Nearest Neighbor Search
Summary: Isolates and accelerates the Distance Comparison Operation (DCO) in high-dimensional AKNN by proposing DADE, a data-aware, unbiased lower-dimensional distance estimator with an optimized formulation. Adds a hypothesis-testing scheme to adaptively pick minimal projection dimensions and plugs into IVF/HNSW to cut DCO-dominated latency. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Liwei Deng (University of Electronic Science and Technology of China)
- 2. Penghao Chen (University of Electronic Science and Technology of China)
- 3. Ximu Zeng (University of Electronic Science and Technology of China)
- 4. Tianfu Wang (University of Science and Technology Beijing)
- 5. Yan Zhao (Shenzhen University)
- 6. Kai Zheng (Shenzhen University)
BibTeX Citation
@article{deng_vldb25,
title = {{Efficient Data-aware Distance Comparison Operations for High-Dimensional Approximate Nearest Neighbor Search}},
author = {Deng, Liwei and Chen, Penghao and Zeng, Ximu and Wang, Tianfu and Zhao, Yan and Zheng, Kai},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {3},
pages = {812--821},
doi = {10.14778/3712221.3712244},
url = {https://doi.org/10.14778/3712221.3712244},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 8 of 8 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 18 of 18 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next