HARMONY: A Scalable Distributed Vector Database for High-Throughput Approximate Nearest Neighbor Search
Summary: Harmony: distributed ANNS with a multi-gran partition (dimension-based + vector-based) for balanced load, reduced comms. Early-stop pruning leverages distance monotonicity to prune, delivering 4.63x throughput on 4 nodes and 58% gains on skewed workloads. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Qian Xu (Renmin University of China)
- 2. Feng Zhang (Renmin University of China)
- 3. Chengxi Li (Renmin University of China)
- 4. Lei Cao (Massachusetts Institute of Technology)
- 5. Zheng Chen (Renmin University of China)
- 6. Jidong Zhai (Tsinghua University)
- 7. Xiaoyong Du (Renmin University of China)
BibTeX Citation
@inproceedings{xu_sigmod26,
title = {{HARMONY: A Scalable Distributed Vector Database for High-Throughput Approximate Nearest Neighbor Search}},
author = {Xu, Qian and Zhang, Feng and Li, Chengxi and Cao, Lei and Chen, Zheng and Zhai, Jidong and Du, Xiaoyong},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3749167},
url = {https://dl.acm.org/doi/10.1145/3749167},
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 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