SeRF: Segment Graph for Range-Filtering Approximate Nearest Neighbor Search
Summary: SeRF introduces a segment graph for range-filtering ANNS; for threshold ranges, the index time/size matches a single ANNS index, with lossless compression of n per-range indexes (Omega(n) savings). A 2D segment graph extends to general ranges, achieving average-case index size O(n log n) and breaking the quadratic barrier; extensive experiments on real data show superior performance and scalability. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Chaoji Zuo (Rutgers University)
- 2. Miao Qiao (University of Auckland)
- 3. Wenchao Zhou (Alibaba)
- 4. Feifei Li (Alibaba)
- 5. Dong Deng (Rutgers University)
BibTeX Citation
@inproceedings{zuo_sigmod24,
title = {{SeRF: Segment Graph for Range-Filtering Approximate Nearest Neighbor Search}},
author = {Zuo, Chaoji and Qiao, Miao and Zhou, Wenchao and Li, Feifei and Deng, Dong},
series = {{SIGMOD} '24},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3639324},
url = {https://dl.acm.org/doi/10.1145/3639324},
year = {2024}
}
Incoming Citations (Sorted by Pagerank)
Showing 30 of 30 citing papers.
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