Improving Approximate Nearest Neighbor Search through Learned Adaptive Early Termination
Summary: Adaptive early termination for ANN via per-query stop-point prediction with gradient-boosted trees. Applied to FAISS-like ANN, it achieves up to 7.1x end-to-end latency reduction at the same accuracy on massive datasets; open-source at github.com/efficient/faiss-learned-termination. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Conglong Li (Carnegie Mellon University)
- 2. Minjia Zhang (Microsoft)
- 3. David G. Andersen (Carnegie Mellon University)
- 4. Yuxiong He (Microsoft)
BibTeX Citation
@inproceedings{li_sigmod20,
title = {{Improving Approximate Nearest Neighbor Search through Learned Adaptive Early Termination}},
author = {Li, Conglong and Zhang, Minjia and Andersen, David G. and He, Yuxiong},
series = {{SIGMOD} '20},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3318464.3380600},
url = {https://dl.acm.org/doi/10.1145/3318464.3380600},
year = {2020}
}Incoming Citations (Sorted by Pagerank)
Showing 39 of 39 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 9 of 9 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 28 | Nearest Neighbor Queries | 1995 | SIGMOD | 0.00051312804 |
| 45 | A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces | 1998 | VLDB | 0.0004503446 |
| 74 | Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph | 2019 | VLDB | 0.00037091678 |
| 298 | Query-Aware Locality-Sensitive Hashing for Approximate Nearest Neighbor Search | 2016 | VLDB | 0.00021833987 |
| 1,409 | Northstar: An Interactive Data Science System | 2018 | VLDB | 0.00010743451 |
| 1,530 | LazyLSH: Approximate Nearest Neighbor Search for Multiple Distance Functions with a Single Index | 2016 | SIGMOD | 0.00010344205 |
| 2,505 | DSH: Data Sensitive Hashing for High-Dimensional k-NN Search | 2014 | SIGMOD | 8.3779738e-05 |
| 4,856 | Neighbor-Sensitive Hashing | 2016 | VLDB | 6.3798143e-05 |
| 4,994 | Online Query Processing: A Tutorial | 2001 | SIGMOD | 6.3234291e-05 |
Previous
Page 1 / 1
Next