Curator: Efficient Vector Search with Low-Selectivity Filters
Summary: Curator targets low-selectivity filtered ANNS, where graph indexes fragment after predicate pruning and degree-boosting fixes are too costly. It uses a dual-index, partition-based design with label-specialized indexes inside a shared clustering tree, preserving graph-based performance while adding incremental updates and complex predicates with little overhead. (summarized by gpt-5.4-mini on Apr 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yicheng Jin (Duke University)
- 2. Yongji Wu (University of California Berkeley)
- 3. Wenjun Hu (Yale University)
- 4. Bruce M. Maggs (Duke University)
- 5. Jun Yang (Duke University)
- 6. Xiao Zhang (Cisco ThousandEyes)
- 7. Danyang Zhuo (Duke University)
BibTeX Citation
@inproceedings{jin_sigmod26,
title = {{Curator: Efficient Vector Search with Low-Selectivity Filters}},
author = {Jin, Yicheng and Wu, Yongji and Hu, Wenjun and Maggs, Bruce M. and Yang, Jun and Zhang, Xiao and Zhuo, Danyang},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786635},
url = {https://dl.acm.org/doi/10.1145/3786635},
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 11 of 11 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next