Efficient and Robust Out-Of-Distribution Vector Similarity Search with Cross-Distribution Monotonic Graph
Summary: CDMG is a graph-based ANN index for OOD vector search that explicitly bridges database/query distribution shift via cross-distribution monotonicity, yielding monotone search paths and improved navigability/clusterability. CDMG+ adds practical construction/query synthesis optimizations, with up to 3.6x speedups on real OOD datasets. (summarized by gpt-5.4-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. Qiang Yue (Hangzhou Dianzi University)
- 2. Mengzhao Wang (Zhejiang University)
- 3. Xiaoliang Xu (Hangzhou Dianzi University)
- 4. Cheng Long (Nanyang Technological University)
- 5. Yuxiang Wang (Hangzhou Dianzi University)
- 6. Jiahui Wang (Hangzhou Dianzi University)
BibTeX Citation
@inproceedings{yue_sigmod26,
title = {{Efficient and Robust Out-Of-Distribution Vector Similarity Search with Cross-Distribution Monotonic Graph}},
author = {Yue, Qiang and Wang, Mengzhao and Xu, Xiaoliang and Long, Cheng and Wang, Yuxiang and Wang, Jiahui},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786643},
url = {https://dl.acm.org/doi/10.1145/3786643},
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 22 of 22 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next