Joint Probability Selection and Power Allocation for Federated Learning
This work addresses the challenge of efficient client selection and resource allocation in federated learning for wireless networks, which is an incremental improvement over existing deterministic methods.
The paper tackles the problem of optimizing federated learning performance over wireless networks with energy-constrained devices by proposing a probabilistic approach to jointly select clients and allocate power, which maximizes the expected number of participating clients and shows significant improvements in energy consumption, completion time, and accuracy compared to benchmarks.
In this paper, we study the performance of federated learning over wireless networks, where devices with a limited energy budget train a machine learning model. The federated learning performance depends on the selection of the clients participating in the learning at each round. Most existing studies suggest deterministic approaches for the client selection, resulting in challenging optimization problems that are usually solved using heuristics, and therefore without guarantees on the quality of the final solution. We formulate a new probabilistic approach to jointly select clients and allocate power optimally so that the expected number of participating clients is maximized. To solve the problem, a new alternating algorithm is proposed, where at each step, the closed-form solutions for user selection probabilities and power allocations are obtained. Our numerical results show that the proposed approach achieves a significant performance in terms of energy consumption, completion time and accuracy as compared to the studied benchmarks.