Integrating Vector Databases across Embedding Models
Summary: Integrates vector DBs built with different embedding models without access to raw data or model internals, enabling cross‑database top‑k similarity search. Relies on an empirical "local isometry" hypothesis with theoretical quality bounds and achieves high top‑k recall across NV‑embed‑V2, OpenAI Ada, GloVe, Mistral, and FastText. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Beining Yang (University of Edinburgh)
- 2. Yang Cao (University of Edinburgh)
- 3. Yang Ren (Huawei)
BibTeX Citation
@inproceedings{yang_sigmod26,
title = {{Integrating Vector Databases across Embedding Models}},
author = {Yang, Beining and Cao, Yang and Ren, Yang},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769803},
url = {https://dl.acm.org/doi/10.1145/3769803},
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 13 of 13 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next