Preprint · 2022 · Open access
Locally Differentially Private Distributed Deep Learning via Knowledge Distillation
arXiv (Cornell University) · Published 7 February 2022 · DOI 10.48550/arxiv.2202.02971
In brief
“Locally Differentially Private Distributed Deep Learning via Knowledge Distillation” is a 2022 preprint by Di Zhuang and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 3
- Most cited in
- 2022 (1)
- References
- 43
- Authors
- 3
Abstract
Deep learning often requires a large amount of data. In real-world applications, e.g., healthcare applications, the data collected by a single organization (e.g., hospital) is often limited, and the majority of massive and diverse data is often segregated across multiple organizations. As such, it motivates the researchers to conduct distributed deep learning, where the data user would like to build DL models using the data segregated across multiple different data owners. However, this could lead to severe privacy concerns due to the sensitive nature of the data, thus the data owners would be hesitant and reluctant to participate. We propose LDP-DL, a privacy-preserving distributed deep learning framework via local differential privacy and knowledge distillation, where each data owner learns a teacher model using its own (local) private dataset, and the data user learns a student model to mimic the output of the ensemble of the teacher models. In the experimental evaluation, a comprehensive comparison has been made among our proposed approach (i.e., LDP-DL), DP-SGD, PATE and DP-FL, using three popular deep learning benchmark datasets (i.e., CIFAR10, MNIST and FashionMNIST). The experimental results show that LDP-DL consistently outperforms the other competitors in terms of privacy budget and model accuracy.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Zhuang, D., Li, M., & Chang, J. M. (2022). Locally Differentially Private Distributed Deep Learning via Knowledge Distillation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2202.02971
MLA 9
Zhuang, Di, et al. “Locally Differentially Private Distributed Deep Learning via Knowledge Distillation.” arXiv (Cornell University), 2022. https://doi.org/10.48550/arxiv.2202.02971.
Chicago
Zhuang, Di, Mingchen Li, and J. Morris Chang. 2022. “Locally Differentially Private Distributed Deep Learning via Knowledge Distillation.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2202.02971.
Harvard
Zhuang, D., Li, M. and Chang, J. M. (2022) ‘Locally Differentially Private Distributed Deep Learning via Knowledge Distillation’, arXiv (Cornell University). doi:10.48550/arxiv.2202.02971.
IEEE
D. Zhuang, M. Li, and J. M. Chang, “Locally Differentially Private Distributed Deep Learning via Knowledge Distillation,” arXiv (Cornell University), 2022, doi: 10.48550/arxiv.2202.02971.
BibTeX
@misc{zhuang2022locally,
title = {{Locally Differentially Private Distributed Deep Learning via Knowledge Distillation}},
author = {Zhuang, Di and Li, Mingchen and Chang, J. Morris},
howpublished = {arXiv (Cornell University)},
year = {2022},
doi = {10.48550/arxiv.2202.02971},
url = {https://doi.org/10.48550/arxiv.2202.02971}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2022 | 1 | |
| 2023 | 1 | |
| 2024 | 1 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- local differential privacy
- distributed deep learning
- knowledge distillation
- privacy-preserving machine learning
- federated learning
- data privacy
- teacher-student models
- privacy-accuracy trade-off
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Zhuang, D., Li, M., & Chang, J. M. (2022). Locally Differentially Private Distributed Deep Learning via Knowledge Distillation. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2202.02971
How many times has this paper been cited?
3 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Di Zhuang, Mingchen Li, J. Morris Chang.
What is the DOI of this paper?
10.48550/arxiv.2202.02971, permanently at https://doi.org/10.48550/arxiv.2202.02971. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.