TaCo: Data-adaptive and Query-aware Subspace Collision for High-dimensional Approximate Nearest Neighbor Search
Summary: TaCo makes subspace collision data-adaptive via entropy-balanced transformations and query-aware through dynamically allocated probing. It delivers up to 8× faster indexing, 0.6× memory use, and 1.5× higher query throughput. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Jiuqi Wei (Ant Financial)
- 2. Zhenyu Liao (Huazhong University of Science and Technology)
- 3. Ruoyu Han (Chinese Academy of Sciences)
- 4. Quanqing Xu (Ant Financial)
- 5. Chuanhui Yang (Ant Financial)
- 6. Themis Palpanas (Université Paris Cité)
BibTeX Citation
@inproceedings{wei_sigmod26,
title = {{TaCo: Data-adaptive and Query-aware Subspace Collision for High-dimensional Approximate Nearest Neighbor Search}},
author = {Wei, Jiuqi and Liao, Zhenyu and Han, Ruoyu and Xu, Quanqing and Yang, Chuanhui and Palpanas, Themis},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802118},
url = {https://dl.acm.org/doi/10.1145/3802118},
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 33 of 33 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next