CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA
Summary: CoTra: distributed ANN/vector search over RDMA, exploiting approximate/asynchronous execution to break the compute–communication tension. Clustered partitioning + task push/batching enable collaborative search that scales to 9.8–13.4x on 16 machines and beats baselines at high recall. (summarized by gpt-5.4-mini on Apr 11 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Xiangyu Zhi (Chinese University of Hong Kong)
- 2. Meng Chen (Fudan University)
- 3. Xiao Yan (Wuhan University)
- 4. Baotong Lu (Microsoft)
- 5. Hui Li (Chinese University of Hong Kong)
- 6. Qianxi Zhang (Microsoft)
- 7. Qi Chen (Microsoft)
- 8. James Cheng (Chinese University of Hong Kong)
BibTeX Citation
@inproceedings{zhi_sigmod26,
title = {{CoTra: Towards Efficient and Scalable Distributed Vector Search with RDMA}},
author = {Zhi, Xiangyu and Chen, Meng and Yan, Xiao and Lu, Baotong and Li, Hui and Zhang, Qianxi and Chen, Qi and Cheng, James},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786634},
url = {https://dl.acm.org/doi/10.1145/3786634},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,525 | Quantization Meets Projection: A Happy Marriage for Approximate k-Nearest Neighbor Search | 2026 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 10 of 10 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next