Towards Client Driven Federated Learning

TL;DR

This paper introduces Client-Driven Federated Learning (CDFL), a novel framework where clients independently update models, enabling better adaptation to dynamic data distributions and improving performance and efficiency.

Contribution

The paper proposes CDFL, a client-driven FL framework that offloads distribution estimation to the server and supports asynchronous client updates, with theoretical convergence analysis.

Findings

CDFL outperforms baseline methods in model accuracy.

CDFL demonstrates improved computational efficiency.

CDFL adapts rapidly to changing data distributions.

Abstract

Conventional federated learning (FL) frameworks follow a server-driven model where the server determines session initiation and client participation, which faces challenges in accommodating clients' asynchronous needs for model updates. We introduce Client-Driven Federated Learning (CDFL), a novel FL framework that puts clients at the driving role. In CDFL, each client independently and asynchronously updates its model by uploading the locally trained model to the server and receiving a customized model tailored to its local task. The server maintains a repository of cluster models, iteratively refining them using received client models. Our framework accommodates complex dynamics in clients' data distributions, characterized by time-varying mixtures of cluster distributions, enabling rapid adaptation to new tasks with superior performance. In contrast to traditional clustered FL protocols that send multiple cluster models to a client to perform distribution estimation, we propose a paradigm that offloads the estimation task to the server and only sends a single model to a client, and novel strategies to improve estimation accuracy. We provide a theoretical analysis of CDFL's convergence. Extensive experiments across various datasets and system settings highlight CDFL's substantial advantages in model performance and computation efficiency over baselines.