CONDA: A Connectivity-Aware Dynamic Index for Approximate Nearest Neighbor Search over Evolving Data
Summary: CONDA is a dynamic graph ANNS index for evolving vectors, combining topology-aware pruning, bidirectional link reinforcement, and lightweight lazy deletion. It preserves connectivity under updates, improving recall by up to 24.5% and update throughput by 1.90×. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Darae Lee (NAVER Corporation)
- 2. Min-Soo Kim (Korea Advanced Institute of Science and Technology)
BibTeX Citation
@article{lee_vldb26,
title = {{CONDA: A Connectivity-Aware Dynamic Index for Approximate Nearest Neighbor Search over Evolving Data}},
author = {Lee, Darae and Kim, Min-Soo},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {11},
pages = {3357--3370},
doi = {10.14778/3836663.3836694},
url = {https://doi.org/10.14778/3836663.3836694},
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 19 of 19 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next