VSAG: An Optimized Search Framework for Graph-based Approximate Nearest Neighbor Search
Summary: VSAG is a production-oriented framework for graph-based ANNS, combining cache-aware prefetching, automatic parameter tuning without index rebuilds, and hardware/quantization-aware distance computation. Deployed at Ant Group, it delivers up to 4× HNSWlib speedup at equal accuracy. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Xiaoyao Zhong (Ant Financial)
- 2. Haotian Li (Ant Financial)
- 3. Jiabao Jin (Ant Financial)
- 4. Mingyu Yang (Ant Financial)
- 5. Deming Chu (Ant Financial)
- 6. Xiangyu Wang (Ant Financial)
- 7. Zhitao Shen (Ant Financial)
- 8. Wei Jia (Ant Financial)
- 9. George Gu (Intel)
- 10. Yi Xie (Intel)
- 11. Xuemin Lin (Shanghai Jiao Tong University)
- 12. Heng Tao Shen (Tongji University)
- 13. Jingkuan Song (Tongji University)
- 14. Peng Cheng (East China Normal University; Tongji University)
BibTeX Citation
@article{zhong_vldb25,
title = {{VSAG: An Optimized Search Framework for Graph-based Approximate Nearest Neighbor Search}},
author = {Zhong, Xiaoyao and Li, Haotian and Jin, Jiabao and Yang, Mingyu and Chu, Deming and Wang, Xiangyu and Shen, Zhitao and Jia, Wei and Gu, George and Xie, Yi and Lin, Xuemin and Shen, Heng Tao and Song, Jingkuan and Cheng, Peng},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {12},
pages = {5017--5030},
doi = {10.14778/3750601.3750624},
url = {https://doi.org/10.14778/3750601.3750624},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,447 | Efficient and Robust Out-Of-Distribution Vector Similarity Search with Cross-Distribution Monotonic Graph | 2026 | SIGMOD | 5.093636e-05 |
| 10,455 | FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search | 2026 | SIGMOD | 5.093636e-05 |
| 10,525 | Quantization Meets Projection: A Happy Marriage for Approximate k-Nearest Neighbor Search | 2026 | VLDB | 5.093636e-05 |
| 10,585 | RED-ANNS: An RDMA-Enabled Distributed Framework for Graph-Based Approximate Nearest Neighbor Search | 2026 | VLDB | 5.093636e-05 |
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