Subspace Collision: An Efficient and Accurate Framework for High-dimensional Approximate Nearest Neighbor Search
Summary: Subspace Collision (SC) yields theoretical guarantees for high-d ANN via SC-score, a Pareto-distance proxy, and SuCo's clustering-based, lightweight index. Experiments show 1-2 orders of magnitude faster queries with <=1/10 memory, beating guarantee-enabled baselines. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jiuqi Wei (Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences)
- 2. Xiaodong Lee (Fuxi Institution; Institute of Computing Technology, Chinese Academy of Sciences)
- 3. Zhenyu Liao (Huazhong University of Science and Technology)
- 4. Themis Palpanas (Paris Cité University)
- 5. Botao Peng (Institute of Computing Technology, Chinese Academy of Sciences)
BibTeX Citation
@inproceedings{wei_sigmod25,
title = {{Subspace Collision: An Efficient and Accurate Framework for High-dimensional Approximate Nearest Neighbor Search}},
author = {Wei, Jiuqi and Lee, Xiaodong and Liao, Zhenyu and Palpanas, Themis and Peng, Botao},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3709729},
url = {https://dl.acm.org/doi/10.1145/3709729},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 7 of 7 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,615 | A Topology-Aware Localized Update Strategy for Graph-Based ANN Index | 2026 | VLDB | 5.8214312e-05 |
| 9,360 | DARTH: Declarative Recall Through Early Termination for Approximate Nearest Neighbor Search | 2026 | SIGMOD | 5.2819088e-05 |
| 10,193 | An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System: [Experiments & Analysis] | 2026 | SIGMOD | 5.093636e-05 |
| 10,297 | TaCo: Data-adaptive and Query-aware Subspace Collision for High-dimensional Approximate Nearest Neighbor Search | 2026 | SIGMOD | 5.093636e-05 |
| 10,362 | Dynamically Detect and Fix Hardness for Efficient Approximate Nearest Neighbor Search | 2026 | SIGMOD | 5.093636e-05 |
| 10,544 | I/O Optimizations for Graph-Based Disk-Resident Approximate Nearest Neighbor Search: A Design Space Exploration | 2026 | VLDB | 5.093636e-05 |
| 10,578 | ConANN: Conformal Approximate Nearest Neighbor Search | 2026 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 31 of 31 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next