DIGRA: A Dynamic Graph Indexing for Approximate Nearest Neighbor Search with Range Filter
Summary: DIGRA introduces a dynamic graph index for range-filtered ANNS on vectors with attributes, addressing update limitations of prior methods. It combines a dynamic multi-way tree, lazy weight-based updates, and integrated ANNS indices to balance query speed, update cost, and indexing overhead for large evolving datasets. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Mengxu Jiang (Chinese University of Hong Kong)
- 2. Zhi Yang (Huazhong University of Science and Technology)
- 3. Fangyuan Zhang (Chinese University of Hong Kong)
- 4. Guanhao Hou (Chinese University of Hong Kong)
- 5. Jieming Shi (Hong Kong Polytechnic University)
- 6. Wenchao Zhou (Alibaba)
- 7. Feifei Li (Alibaba)
- 8. Sibo Wang (Chinese University of Hong Kong)
BibTeX Citation
@inproceedings{jiang_sigmod25,
title = {{DIGRA: A Dynamic Graph Indexing for Approximate Nearest Neighbor Search with Range Filter}},
author = {Jiang, Mengxu and Yang, Zhi and Zhang, Fangyuan and Hou, Guanhao and Shi, Jieming and Zhou, Wenchao and Li, Feifei and Wang, Sibo},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3725399},
url = {https://dl.acm.org/doi/10.1145/3725399},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 10 of 10 citing papers.
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