Fast Decentralized Gradient Tracking for Federated Minimax Optimization with Local Updates
It addresses communication efficiency and robustness in federated learning for distributed nodes with data heterogeneity, representing an incremental advance.
The paper tackles federated minimax optimization by proposing K-GT-Minimax, a decentralized algorithm combining local updates and gradient tracking, achieving a superior convergence rate for nonconvex-strongly-concave problems.
Federated learning (FL) for minimax optimization has emerged as a powerful paradigm for training models across distributed nodes/clients while preserving data privacy and model robustness on data heterogeneity. In this work, we delve into the decentralized implementation of federated minimax optimization by proposing \texttt{K-GT-Minimax}, a novel decentralized minimax optimization algorithm that combines local updates and gradient tracking techniques. Our analysis showcases the algorithm's communication efficiency and convergence rate for nonconvex-strongly-concave (NC-SC) minimax optimization, demonstrating a superior convergence rate compared to existing methods. \texttt{K-GT-Minimax}'s ability to handle data heterogeneity and ensure robustness underscores its significance in advancing federated learning research and applications.