Communication and Energy Efficient Federated Learning using Zero-Order Optimization Technique
This addresses communication and energy efficiency for resource-constrained devices in federated learning, but it is incremental as it builds on existing optimization techniques.
The paper tackles the communication and energy bottlenecks in federated learning by proposing a zero-order optimization method that reduces uploads to a single quantized scalar per device per iteration, showing superiority over standard gradient-based methods in communication overhead and energy consumption.
Federated learning (FL) is a popular machine learning technique that enables multiple users to collaboratively train a model while maintaining the user data privacy. A significant challenge in FL is the communication bottleneck in the upload direction, and thus the corresponding energy consumption of the devices, attributed to the increasing size of the model/gradient. In this paper, we address this issue by proposing a zero-order (ZO) optimization method that requires the upload of a quantized single scalar per iteration by each device instead of the whole gradient vector. We prove its theoretical convergence and find an upper bound on its convergence rate in the non-convex setting, and we discuss its implementation in practical scenarios. Our FL method and the corresponding convergence analysis take into account the impact of quantization and packet dropping due to wireless errors. We show also the superiority of our method, in terms of communication overhead and energy consumption, as compared to standard gradient-based FL methods.