Federated Block Coordinate Descent Scheme for Learning Global and Personalized Models

TL;DR

This paper introduces a federated learning framework that personalizes models while efficiently handling heterogeneous device training times through a hierarchical block coordinate descent scheme, improving convergence and latency.

Contribution

It proposes a novel quadratic penalty formulation for personalized federated learning and a hierarchical block coordinate descent algorithm with communication protocols for improved efficiency.

Findings

Theoretical convergence rate established for the proposed algorithm.

Asynchronous protocol reduces latency significantly.

Experimental results show faster convergence for personalized models.

Abstract

In federated learning, models are learned from users' data that are held private in their edge devices, by aggregating them in the service provider's "cloud" to obtain a global model. Such global model is of great commercial value in, e.g., improving the customers' experience. In this paper we focus on two possible areas of improvement of the state of the art. First, we take the difference between user habits into account and propose a quadratic penalty-based formulation, for efficient learning of the global model that allows to personalize local models. Second, we address the latency issue associated with the heterogeneous training time on edge devices, by exploiting a hierarchical structure modeling communication not only between the cloud and edge devices, but also within the cloud. Specifically, we devise a tailored block coordinate descent-based computation scheme, accompanied with communication protocols for both the synchronous and asynchronous cloud settings. We characterize the theoretical convergence rate of the algorithm, and provide a variant that performs empirically better. We also prove that the asynchronous protocol, inspired by multi-agent consensus technique, has the potential for large gains in latency compared to a synchronous setting when the edge-device updates are intermittent. Finally, experimental results are provided that corroborate not only the theory, but also show that the system leads to faster convergence for personalized models on the edge devices, compared to the state of the art.