Differentially Private Federated Learning for Multitask Objective Recognition | IEEE Journals & Magazine | IEEE Xplore

Differentially Private Federated Learning for Multitask Objective Recognition


Abstract:

Many machine learning models are naturally multitask, which may involve regression and classification tasks, in which they can be trained by the multitask network to yiel...Show More

Abstract:

Many machine learning models are naturally multitask, which may involve regression and classification tasks, in which they can be trained by the multitask network to yield a more generalized model with the aid of correlated features. When these learning models are deployed on Internet-of-Things devices, the computation efficiency and the privacy of the data can pose a significant challenge to developing a federated learning (FL) algorithm for both higher learning performance and better privacy protection. In this article, a new FL framework is proposed for a class of multitask learning problems with hard parameter-sharing model through which the learning tasks are reformulated as a multiobjective optimization problem for better performance. Specifically, the stochastic multiple gradient descent approach and differential privacy are integrated into this FL algorithm for achieving a Pareto optimality that obtains a good tradeoff among different learning tasks while providing data protection. The outstanding performance of this algorithm is demonstrated by the empirical experiments on multiMINIST, the Chinese city parking dataset, and Cityscapes dataset.
Published in: IEEE Transactions on Industrial Informatics ( Volume: 20, Issue: 5, May 2024)
Page(s): 7269 - 7281
Date of Publication: 08 February 2024

ISSN Information:

Funding Agency:


References

References is not available for this document.