Preprint · 2017 · Open access
Differentially Private Distributed Learning for Language Modeling Tasks
arXiv (Cornell University) · Published 20 December 2017 · DOI 10.48550/arxiv.1712.07473
In brief
“Differentially Private Distributed Learning for Language Modeling Tasks” is a 2017 preprint by Popov, Vadim and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 3 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 3
- Most cited in
- 2019 (1)
- References
- 27
- Authors
- 5
Abstract
One of the big challenges in machine learning applications is that training data can be different from the real-world data faced by the algorithm. In language modeling, users' language (e.g. in private messaging) could change in a year and be completely different from what we observe in publicly available data. At the same time, public data can be used for obtaining general knowledge (i.e. general model of English). We study approaches to distributed fine-tuning of a general model on user private data with the additional requirements of maintaining the quality on the general data and minimization of communication costs. We propose a novel technique that significantly improves prediction quality on users' language compared to a general model and outperforms gradient compression methods in terms of communication efficiency. The proposed procedure is fast and leads to an almost 70% perplexity reduction and 8.7 percentage point improvement in keystroke saving rate on informal English texts. We also show that the range of tasks our approach is applicable to is not limited by language modeling only. Finally, we propose an experimental framework for evaluating differential privacy of distributed training of language models and show that our approach has good privacy guarantees.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Vadim, P., Kudinov, M., Piontkovskaya, I., Vytovtov, P., & Nevidomsky, A. (2017). Differentially Private Distributed Learning for Language Modeling Tasks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1712.07473
MLA 9
Vadim, Popov,, et al. “Differentially Private Distributed Learning for Language Modeling Tasks.” arXiv (Cornell University), 2017. https://doi.org/10.48550/arxiv.1712.07473.
Chicago
Vadim, Popov,, Mikhail Kudinov, Irina Piontkovskaya, Petr Vytovtov, and Alex Nevidomsky. 2017. “Differentially Private Distributed Learning for Language Modeling Tasks.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1712.07473.
Harvard
Vadim, P. et al. (2017) ‘Differentially Private Distributed Learning for Language Modeling Tasks’, arXiv (Cornell University). doi:10.48550/arxiv.1712.07473.
IEEE
P. Vadim, M. Kudinov, I. Piontkovskaya, P. Vytovtov, and A. Nevidomsky, “Differentially Private Distributed Learning for Language Modeling Tasks,” arXiv (Cornell University), 2017, doi: 10.48550/arxiv.1712.07473.
BibTeX
@misc{vadim2017differentially,
title = {{Differentially Private Distributed Learning for Language Modeling Tasks}},
author = {Vadim, Popov, and Kudinov, Mikhail and Piontkovskaya, Irina and Vytovtov, Petr and Nevidomsky, Alex},
howpublished = {arXiv (Cornell University)},
year = {2017},
doi = {10.48550/arxiv.1712.07473},
url = {https://doi.org/10.48550/arxiv.1712.07473}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2019 | 1 | |
| 2020 | 1 | |
| 2023 | 1 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- differential privacy
- distributed learning
- language modeling
- private messaging
- fine-tuning
- communication efficiency
- gradient compression
- informal English
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?
Vadim, P., Kudinov, M., Piontkovskaya, I., Vytovtov, P., & Nevidomsky, A. (2017). Differentially Private Distributed Learning for Language Modeling Tasks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1712.07473
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?
Popov, Vadim, Mikhail Kudinov, Irina Piontkovskaya, Petr Vytovtov, Alex Nevidomsky.
What is the DOI of this paper?
10.48550/arxiv.1712.07473, permanently at https://doi.org/10.48550/arxiv.1712.07473. 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.