Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques
This work provides a unified framework for optimizing personalized federated learning models, potentially reducing the need for task-specific optimizers, which is incremental but broadens applicability in distributed machine learning.
The paper tackles the optimization challenges in personalized federated learning by proposing general optimizers, such as tailored Local SGD and accelerated coordinate descent variants, that apply to many existing objectives, achieving best-known communication and computation guarantees.
We investigate the optimization aspects of personalized Federated Learning (FL). We propose general optimizers that can be applied to numerous existing personalized FL objectives, specifically a tailored variant of Local SGD and variants of accelerated coordinate descent/accelerated SVRCD. By examining a general personalized objective capable of recovering many existing personalized FL objectives as special cases, we develop a comprehensive optimization theory applicable to a wide range of strongly convex personalized FL models in the literature. We showcase the practicality and/or optimality of our methods in terms of communication and local computation. Remarkably, our general optimization solvers and theory can recover the best-known communication and computation guarantees for addressing specific personalized FL objectives. Consequently, our proposed methods can serve as universal optimizers, rendering the design of task-specific optimizers unnecessary in many instances.