Differentially Private Federated Learning for Multitask Objective Recognition

Renyou Xie

doi:10.1109/TII.2023.3342897

Differentially Private Federated Learning for Multitask Objective Recognition

2024-05-01

2

PRE

AI

DOI：10.1109/TII.2023.3342897

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Task analysis

Computational modeling

Optimization

Federated learning

Deep learning

Training

Servers

Differential privacy (DP)

federated learning (FL)

multiobjective optimization (MOO)

objective recognition

Differentially Private Federated Learning for Multitask Objective Recognition

Abstract

Journal

Organization