ANNiE: A Learned Query Cost Estimator for Graph-Based Approximate Nearest Neighbor Search
Summary: ANNiE introduces learned cost estimation for graph-based ANNS, predicting effort to meet a target recall with probabilistic guarantees. Its cost-based search, ANNiE-S, automatically meets per-query recall targets and delivers 2.3× speedups. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zeyu Wang (Fudan University)
- 2. Manos Chatzakis (Université Paris Cité)
- 3. Qitong Wang (Harvard University)
- 4. Themis Palpanas (Université Paris Cité)
- 5. Peng Wang (Fudan University)
- 6. Wei Wang (Fudan University)
BibTeX Citation
@article{wang_vldb26,
title = {{ANNiE: A Learned Query Cost Estimator for Graph-Based Approximate Nearest Neighbor Search}},
author = {Wang, Zeyu and Chatzakis, Manos and Wang, Qitong and Palpanas, Themis and Wang, Peng and Wang, Wei},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {11},
pages = {3820--3833},
doi = {10.14778/3836663.3836728},
url = {https://doi.org/10.14778/3836663.3836728},
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 20 of 20 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next