Skip to content

whopriyam/Benchmarking-Differential-Privacy-and-Federated-Learning-for-BERT-Models

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

62 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Benchmarking Differential Privacy and Federated Learning for BERT Models

Made With python 3.8.2MaintenanceOpen Source Love svg1Pytorch

Abstract

Natural Language Processing (NLP) techniques can be applied to help with the diagnosis of medical conditions such as depression, using a collection of a person's utterances. Depression is a serious medical illness that can have adverse effects on how one feels, thinks, and acts, which can lead to emotional and physical problems. Due to the sensitive nature of such data, privacy measures need to be taken for handling and training models with such data. In this work, we study the effects that the application of Differential Privacy (DP) has, in both a centralized and a Federated Learning (FL) setup, on training contextualized language models (BERT, ALBERT, RoBERTa and DistilBERT). We offer insights on how to privately train NLP models and what architectures and setups provide more desirable privacy utility trade-offs. We envisage this work to be used in future healthcare and mental health studies to keep medical history private. Therefore, we provide an open-source implementation of this work.

Paper

https://arxiv.org/abs/2106.13973

Citation

@article{basu2021benchmarking, title={Benchmarking differential privacy and federated learning for bert models}, author={Basu, Priyam and Roy, Tiasa Singha and Naidu, Rakshit and Muftuoglu, Zumrut and Singh, Sahib and Mireshghallah, Fatemehsadat}, journal={arXiv preprint arXiv:2106.13973}, year={2021} }

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •