ConANN: Conformal Approximate Nearest Neighbor Search
Summary: ConANN applies conformal risk control to IVF ANN to deliver the first distribution‑free formal guarantees on approximation error (FNR). It adaptively probes clusters per query, often reducing probes and adding negligible overhead while matching target FNR. (summarized by gpt-5-mini on Mar 13 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Sonia Horchidan (KTH Royal Institute of Technology)
- 2. Fabian Zeiher (KTH Royal Institute of Technology)
- 3. Henrik Boström (KTH Royal Institute of Technology)
- 4. Paris Carbone (KTH Royal Institute of Technology)
BibTeX Citation
@article{horchidan_vldb26,
title = {{ConANN: Conformal Approximate Nearest Neighbor Search}},
author = {Horchidan, Sonia and Zeiher, Fabian and Boström, Henrik and Carbone, Paris},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {1},
pages = {29--42},
doi = {10.14778/3772181.3772184},
url = {https://doi.org/10.14778/3772181.3772184},
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 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