Robust Decentralized Learning with Local Updates and Gradient Tracking
This addresses robustness and efficiency challenges in distributed applications like Federated Learning and IoT, but it is incremental as it builds on existing decentralized and minimax optimization techniques.
The paper tackles data heterogeneity and adversarial robustness in decentralized learning by proposing Dec-FedTrack, a method using local updates and gradient tracking for minimax optimization, proving convergence to a stationary point in nonconvex-strongly concave settings and supporting this with numerical experiments.
As distributed learning applications such as Federated Learning, the Internet of Things (IoT), and Edge Computing grow, it is critical to address the shortcomings of such technologies from a theoretical perspective. As an abstraction, we consider decentralized learning over a network of communicating clients or nodes and tackle two major challenges: data heterogeneity and adversarial robustness. We propose a decentralized minimax optimization method that employs two important modules: local updates and gradient tracking. Minimax optimization is the key tool to enable adversarial training for ensuring robustness. Having local updates is essential in Federated Learning (FL) applications to mitigate the communication bottleneck, and utilizing gradient tracking is essential to proving convergence in the case of data heterogeneity. We analyze the performance of the proposed algorithm, Dec-FedTrack, in the case of nonconvex-strongly concave minimax optimization, and prove that it converges a stationary point. We also conduct numerical experiments to support our theoretical findings.