FedADMM-InSa: An Inexact and Self-Adaptive ADMM for Federated Learning
This work addresses the problem of efficient and robust federated learning for distributed systems with heterogeneous data and resources, representing an incremental improvement over existing FedADMM methods.
The paper tackles the challenge of hyperparameter sensitivity in federated learning by proposing FedADMM-InSa, an inexact and self-adaptive ADMM algorithm that reduces local computational load and accelerates learning compared to vanilla FedADMM, as validated by experiments on synthetic and real-world datasets.
Federated learning (FL) is a promising framework for learning from distributed data while maintaining privacy. The development of efficient FL algorithms encounters various challenges, including heterogeneous data and systems, limited communication capacities, and constrained local computational resources. Recently developed FedADMM methods show great resilience to both data and system heterogeneity. However, they still suffer from performance deterioration if the hyperparameters are not carefully tuned. To address this issue, we propose an inexact and self-adaptive FedADMM algorithm, termed FedADMM-InSa. First, we design an inexactness criterion for the clients' local updates to eliminate the need for empirically setting the local training accuracy. This inexactness criterion can be assessed by each client independently based on its unique condition, thereby reducing the local computational cost and mitigating the undesirable straggle effect. The convergence of the resulting inexact ADMM is proved under the assumption of strongly convex loss functions. Additionally, we present a self-adaptive scheme that dynamically adjusts each client's penalty parameter, enhancing algorithm robustness by mitigating the need for empirical penalty parameter choices for each client. Extensive numerical experiments on both synthetic and real-world datasets are conducted. As validated by some numerical tests, our proposed algorithm can reduce the clients' local computational load significantly and also accelerate the learning process compared to the vanilla FedADMM.