MicroNN: An On-device Disk-resident Updatable Vector Database
Summary: On-device, disk-resident vector search for updatable workloads with hybrid queries (NN + attribute filters) under tight memory. Embeddable MicroNN supports continuous inserts/deletes and delivers ~7 ms top-100 with 90% recall on a million-scale benchmark using ~10 MB RAM. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jeffrey Pound (Apple)
- 2. Floris Chabert (Apple)
- 3. Arjun Bhushan (Apple)
- 4. Ankur Goswami (Apple)
- 5. Anil Pacaci (Apple)
- 6. Shihabur Rahman Chowdhury (Apple)
BibTeX Citation
@inproceedings{pound_sigmod25,
title = {{MicroNN: An On-device Disk-resident Updatable Vector Database}},
author = {Pound, Jeffrey and Chabert, Floris and Bhushan, Arjun and Goswami, Ankur and Pacaci, Anil and Chowdhury, Shihabur Rahman},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3722212.3724444},
url = {https://dl.acm.org/doi/10.1145/3722212.3724444},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,251 | GPS: Revisiting the Data Layout for Disk-based High-Dimensional Vector Search | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 10 of 10 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next