Logo image
Privacy-Preserving Federated Primal-Dual Learning for Non-Convex Problems With Non-Smooth Regularization
Conference paper

Privacy-Preserving Federated Primal-Dual Learning for Non-Convex Problems With Non-Smooth Regularization

Yiwei Li, Chien-Wei Huang, Shuai Wang, Chong-Yung Chi and Tony Q. S. Quek
IEEE International Workshop on Machine Learning for Signal Processing, MLSP, Vol.2023-September
2023

Abstract

differential privacy Federated learning non-convex and non-smooth optimization primal-dual method Human-Computer Interaction Signal Processing
Recently, the federated learning (FL) has been a machine learning paradigm for the preservation of data privacy, though high communication cost and privacy protection are still the main concerns of FL. However, in many practical applications, the trained model needs certain nature or characteristics, such as sparseness in classification, otherwise learning performance loss is inevitable. In order to upgrade the learning performance, a suitable non-smooth regularizer (e.g., ℓ1-norm for the model sparseness) can be added to the loss function (often non-convex) in the considered optimization problem. This paper proposes a novel primal-dual learning algorithm to handle such non-smooth regularization aided non-convex FL problems, that yields much superior learning performance over some state-of-the-art FL algorithms under privacy guarantee by means of differential privacy. Finally, some experimental results are provided to demonstrate the efficacy of the proposed algorithm.

Metrics

1 Record Views

Details

Logo image