Decentralized Personalized Federated Learning for Min-Max Problems

TL;DR

This paper extends personalized federated learning to saddle point problems, introducing decentralized algorithms with theoretical guarantees and demonstrating their effectiveness on bilinear and neural network tasks.

Contribution

It is the first to study decentralized PFL for saddle point problems, broadening the scope beyond minimization tasks with new algorithms and theoretical analysis.

Findings

Proposed algorithms for decentralized saddle point PFL.

Theoretical convergence guarantees for convex-concave problems.

Numerical experiments show improved performance on neural networks.

Abstract

Personalized Federated Learning (PFL) has witnessed remarkable advancements, enabling the development of innovative machine learning applications that preserve the privacy of training data. However, existing theoretical research in this field has primarily focused on distributed optimization for minimization problems. This paper is the first to study PFL for saddle point problems encompassing a broader range of optimization problems, that require more than just solving minimization problems. In this work, we consider a recently proposed PFL setting with the mixing objective function, an approach combining the learning of a global model together with locally distributed learners. Unlike most previous work, which considered only the centralized setting, we work in a more general and decentralized setup that allows us to design and analyze more practical and federated ways to connect devices to the network. We proposed new algorithms to address this problem and provide a theoretical analysis of the smooth (strongly) convex-(strongly) concave saddle point problems in stochastic and deterministic cases. Numerical experiments for bilinear problems and neural networks with adversarial noise demonstrate the effectiveness of the proposed methods.