Multi-Edge Server-Assisted Dynamic Federated Learning with an Optimized Floating Aggregation Point

TL;DR

This paper introduces a cooperative, dynamic federated learning framework with a floating aggregation point that adapts to network changes, optimizing model training across devices and edge servers in real-time environments.

Contribution

It proposes a novel distributed ML architecture with a floating aggregation point and network-aware optimization, addressing heterogeneity and mobility in federated learning environments.

Findings

Convergence analysis of the proposed CE-FL framework.

Effective optimization of network elements improves learning performance.

Validation on real-world testbed demonstrates practical benefits.

Abstract

We propose cooperative edge-assisted dynamic federated learning (CE-FL). CE-FL introduces a distributed machine learning (ML) architecture, where data collection is carried out at the end devices, while the model training is conducted cooperatively at the end devices and the edge servers, enabled via data offloading from the end devices to the edge servers through base stations. CE-FL also introduces floating aggregation point, where the local models generated at the devices and the servers are aggregated at an edge server, which varies from one model training round to another to cope with the network evolution in terms of data distribution and users' mobility. CE-FL considers the heterogeneity of network elements in terms of communication/computation models and the proximity to one another. CE-FL further presumes a dynamic environment with online variation of data at the network devices which causes a drift at the ML model performance. We model the processes taken during CE-FL, and conduct analytical convergence analysis of its ML model training. We then formulate network-aware CE-FL which aims to adaptively optimize all the network elements via tuning their contribution to the learning process, which turns out to be a non-convex mixed integer problem. Motivated by the large scale of the system, we propose a distributed optimization solver to break down the computation of the solution across the network elements. We finally demonstrate the effectiveness of our framework with the data collected from a real-world testbed.