RAIRS: Optimizing Redundant Assignment and List Layout for IVF-Based ANN Search
Summary: RAIRS improves IVF ANN via smarter redundant assignment in Euclidean space: AIR chooses secondary lists using both distance and direction, unlike centroid-only heuristics. SEIL reorders shared postings to cut duplicate distance computations, yielding up to 1.33x faster search. (summarized by gpt-5-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. Zehai Yang (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences)
- 2. Shimin Chen (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences)
BibTeX Citation
@inproceedings{yang_sigmod26,
title = {{RAIRS: Optimizing Redundant Assignment and List Layout for IVF-Based ANN Search}},
author = {Yang, Zehai and Chen, Shimin},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786687},
url = {https://dl.acm.org/doi/10.1145/3786687},
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 15 of 15 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next