Learner Referral for Cost-Effective Federated Learning Over Hierarchical IoT Networks
This work addresses cost and fairness issues in federated learning for hierarchical IoT networks, which is incremental as it builds on existing FL methods with new referral and optimization techniques.
The paper tackles the problem of federated learning (FL) not being applicable when not all clients are registered, by proposing joint learner referral aided federated client selection (LRef-FedCS) with resource scheduling and local model accuracy optimization to minimize worst-case participant cost and ensure long-term fairness in hierarchical IoT networks. Numerical simulations on MNIST/CIFAR-10 datasets show that LRef-FedCS achieves a balance between high global accuracy and reduced cost.
The paradigm of federated learning (FL) to address data privacy concerns by locally training parameters on resource-constrained clients in a distributed manner has garnered significant attention. Nonetheless, FL is not applicable when not all clients within the coverage of the FL server are registered with the FL network. To bridge this gap, this paper proposes joint learner referral aided federated client selection (LRef-FedCS), along with communications and computing resource scheduling, and local model accuracy optimization (LMAO) methods. These methods are designed to minimize the cost incurred by the worst-case participant and ensure the long-term fairness of FL in hierarchical Internet of Things (HieIoT) networks. Utilizing the Lyapunov optimization technique, we reformulate the original problem into a stepwise joint optimization problem (JOP). Subsequently, to tackle the mixed-integer non-convex JOP, we separatively and iteratively address LRef-FedCS and LMAO through the centralized method and self-adaptive global best harmony search (SGHS) algorithm, respectively. To enhance scalability, we further propose a distributed LRef-FedCS approach based on a matching game to replace the centralized method described above. Numerical simulations and experimental results on the MNIST/CIFAR-10 datasets demonstrate that our proposed LRef-FedCS approach could achieve a good balance between pursuing high global accuracy and reducing cost.