FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search
Summary: FGIM studies a new problem for graph-based ANNS: merging multiple existing indexes into one, motivated by cluster consolidation and read-write contention in vector DBs. It uses cross-querying PGs→kNNG, refinement, and kNNG→PG conversion to preserve connectivity/navigability, speeding merges up to 3.5x over HNSW incremental build. (summarized by gpt-5-mini on Apr 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zekai Wu (East China Normal University)
- 2. Jiabao Jin (Ant Financial)
- 3. Peng Cheng (Tongji University)
- 4. Xiaoyao Zhong (Ant Financial)
- 5. Lei Chen (Hong Kong University of Science and Technology)
- 6. Yongxin Tong (Beihang University)
- 7. Zhitao Shen (Ant Financial)
- 8. Jingkuan Song (Tongji University)
- 9. Heng Tao Shen (Tongji University)
- 10. Xuemin Lin (Shanghai Jiao Tong University)
BibTeX Citation
@inproceedings{wu_sigmod26,
title = {{FGIM: a Fast Graph-based Indexes Merging Framework for Approximate Nearest Neighbor Search}},
author = {Wu, Zekai and Jin, Jiabao and Cheng, Peng and Zhong, Xiaoyao and Chen, Lei and Tong, Yongxin and Shen, Zhitao and Song, Jingkuan and Shen, Heng Tao and Lin, Xuemin},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786651},
url = {https://dl.acm.org/doi/10.1145/3786651},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 14 of 14 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next