NeurStore: Efficient In-database Deep Learning Model Management System
Summary: NeurStore stores models at tensor granularity, using HNSW to index tensors and delta-based deduplication plus delta quantization for high-ratio, bounded-loss compression. Compression-aware loading enables compute on compressed tensors, cutting storage and keeping load throughput competitive. (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. Siqi Xiang (National University of Singapore)
- 2. Sheng Wang (Alibaba)
- 3. Xiaokui Xiao (National University of Singapore)
- 4. Cong Yue (National University of Singapore)
- 5. Zhanhao Zhao (National University of Singapore)
- 6. Beng Chin Ooi (Zhejiang University)
BibTeX Citation
@inproceedings{xiang_sigmod26,
title = {{NeurStore: Efficient In-database Deep Learning Model Management System}},
author = {Xiang, Siqi and Wang, Sheng and Xiao, Xiaokui and Yue, Cong and Zhao, Zhanhao and Ooi, Beng Chin},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769809},
url = {https://dl.acm.org/doi/10.1145/3769809},
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 20 of 20 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 13,483 | Using Deep Learning Models to Replace Large Materialized Views in Relational Database | 2021 | CIDR |
| 2 | 8,750 | nsDB: Architecting the Next Generation Database by Integrating Neural and Symbolic Systems | 2024 | VLDB |
| 3 | 559 | Plan-Structured Deep Neural Network Models for Query Performance Prediction | 2019 | VLDB |
| 4 | 3,101 | DeepSqueeze: Deep Semantic Compression for Tabular Data | 2020 | SIGMOD |
| 5 | 11,281 | MetaStore: Analyzing Deep Learning Meta-Data at Scale | 2024 | VLDB |
| 6 | 9,561 | Experimental Analysis of Large-scale Learnable Vector Storage Compression | 2024 | VLDB |
| 7 | 10,656 | NeurIDA: Dynamic Modeling for Effective In-Database Analytics | 2026 | VLDB |
| 8 | 10,669 | QStore: Quantization-Aware Compressed Model Storage | 2026 | VLDB |
| 9 | 6,741 | Serving Deep Learning Models with Deduplication from Relational Databases | 2022 | VLDB |
| 10 | 8,266 | NeurDB: On the Design and Implementation of an AI-powered Autonomous Database | 2025 | CIDR |