VSAG: An Optimized Search Framework for Graph-based Approximate Nearest Neighbor Search
Summary: VSAG: an open-source production framework that accelerates graph-based ANNS by reducing L3 cache misses (prefetching + cache-friendly vector layout) and cutting distance costs via hardware-aware low-precision/scalar quantization. It also auto-tunes algorithm parameters without index rebuilds; deployed at Ant Group and shows up to 4× speedup over HNSWlib at equal accuracy on real datasets. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Xiaoyao Zhong
- 2. Haotian Li
- 3. Jiabao Jin
- 4. Mingyu Yang
- 5. Deming Chu
- 6. Xiangyu Wang
- 7. Zhitao Shen
- 8. Wei Jia
- 9. George Gu
- 10. Yi Xie
- 11. Xuemin Lin
- 12. Heng Tao Shen
- 13. Jingkuan Song
- 14. Peng Cheng
Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,158 | Efficient and Robust Out-Of-Distribution Vector Similarity Search with Cross-Distribution Monotonic Graph | 2026 | SIGMOD | 4.1945683e-05 |
| 10,166 | FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search | 2026 | SIGMOD | 4.1945683e-05 |
| 10,237 | Quantization Meets Projection: A Happy Marriage for Approximate k-Nearest Neighbor Search | 2026 | VLDB | 4.1945683e-05 |
| 10,287 | RED-ANNS: An RDMA-Enabled Distributed Framework for Graph-Based Approximate Nearest Neighbor Search | 2026 | VLDB | 4.1945683e-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