Privacy and Accuracy-Aware AI/ML Model Deduplication
Summary: Formalizes DP-trained model deduplication, marrying privacy budgets with accuracy guarantees. Greedy base-model assignment and Sparse Vector Technique-based private validation curb storage and privacy costs; yields up to 35x compression and 43x speedup. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Hong Guan (Arizona State University)
- 2. Lei Yu (Rensselaer Polytechnic Institute)
- 3. Lixi Zhou (Arizona State University)
- 4. Li Xiong (Emory University)
- 5. Kanchan Chowdhury (Arizona State University)
- 6. Lulu Xie (Arizona State University)
- 7. Xusheng Xiao (Arizona State University)
- 8. Jia Zou (Arizona State University)
BibTeX Citation
@inproceedings{guan_sigmod25,
title = {{Privacy and Accuracy-Aware AI/ML Model Deduplication}},
author = {Guan, Hong and Yu, Lei and Zhou, Lixi and Xiong, Li and Chowdhury, Kanchan and Xie, Lulu and Xiao, Xusheng and Zou, Jia},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3725340},
url = {https://dl.acm.org/doi/10.1145/3725340},
year = {2025}
}
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,224 | DP-S4S: Accurate and Scalable Select-Join-Aggregate Query Processing with User-Level Differential Privacy | 2026 | SIGMOD | 5.093636e-05 |
| 10,466 | InferF: Declarative Factorization of AI/ML Inferences over Joins | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 24 of 24 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 | 70 | Privacy-Preserving Data Mining | 2000 | SIGMOD |
| 2 | 10,282 | Prism: Private Relational Data Synthesis with Language Models | 2026 | SIGMOD |
| 3 | 10,614 | LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning | 2026 | VLDB |
| 4 | 8,843 | Cache Me If You Can: Accuracy-Aware Inference Engine for Differentially Private Data Exploration | 2023 | VLDB |
| 5 | 9,310 | LLM-PBE: Assessing Data Privacy in Large Language Models | 2024 | VLDB |
| 6 | 3,232 | Privacy-preserving Anonymization of Set-valued Data | 2008 | VLDB |
| 7 | 7,841 | Quantifying identifiability to choose and audit epsilon in differentially private deep learning | 2021 | VLDB |
| 8 | 10,335 | A General Framework for Per-record Differential Privacy | 2026 | SIGMOD |
| 9 | 10,024 | Near-Duplicate Sequence Search at Scale for Large Language Model Memorization Evaluation | 2023 | SIGMOD |
| 10 | 6,708 | Serving Deep Learning Models with Deduplication from Relational Databases | 2022 | VLDB |