Compositional federated learning: Applications in distributionally robust averaging and meta learning
This work addresses challenges in federated learning for data mining and machine learning problems with hierarchical structures, such as distributionally robust averaging and meta-learning, though it appears incremental by adapting existing optimization techniques.
The paper tackles the problem of compositional federated learning by proposing a new framework and algorithm that bridges federated learning with compositional stochastic optimization, achieving a convergence rate of O(1/√T) and applying it to distributionally robust federated learning and meta-learning tasks.
In the paper, we propose an effective and efficient Compositional Federated Learning (ComFedL) algorithm for solving a new compositional Federated Learning (FL) framework, which frequently appears in many data mining and machine learning problems with a hierarchical structure such as distributionally robust FL and model-agnostic meta learning (MAML). Moreover, we study the convergence analysis of our ComFedL algorithm under some mild conditions, and prove that it achieves a convergence rate of $O(\frac{1}{\sqrt{T}})$, where $T$ denotes the number of iteration. To the best of our knowledge, our new Compositional FL framework is the first work to bridge federated learning with composition stochastic optimization. In particular, we first transform the distributionally robust FL (i.e., a minimax optimization problem) into a simple composition optimization problem by using KL divergence regularization. At the same time, we also first transform the distribution-agnostic MAML problem (i.e., a minimax optimization problem) into a simple yet effective composition optimization problem. Finally, we apply two popular machine learning tasks, i.e., distributionally robust FL and MAML to demonstrate the effectiveness of our algorithm.