Accelerating Approximate Nearest Neighbor Search in Hierarchical Graphs: Efficient Level Navigation with Shortcuts
Summary: SHG accelerates hierarchical ANN search by skipping redundant intermediate levels via shortcuts that safely determine navigation jumps, combined with hierarchical vector compression. It delivers 1.5–1.8× speedups and up to 20% higher recall over state-of-the-art indexes. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zengyang Gong (Hong Kong University of Science and Technology)
- 2. Yuxiang Zeng (Beihang University)
- 3. Lei Chen (FYTRI; Hong Kong University of Science and Technology)
BibTeX Citation
@article{gong_vldb25,
title = {{Accelerating Approximate Nearest Neighbor Search in Hierarchical Graphs: Efficient Level Navigation with Shortcuts}},
author = {Gong, Zengyang and Zeng, Yuxiang and Chen, Lei},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {10},
pages = {3518--3530},
doi = {10.14778/3748191.3748212},
url = {https://doi.org/10.14778/3748191.3748212},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,297 | TaCo: Data-adaptive and Query-aware Subspace Collision for High-dimensional Approximate Nearest Neighbor Search | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 14 of 14 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next