Decentralized Event-Triggered Federated Learning with Heterogeneous Communication Thresholds

04/07/2022
by   Shahryar Zehtabi, et al.
0

A recent emphasis of distributed learning research has been on federated learning (FL), in which model training is conducted by the data-collecting devices. Existing research on FL has mostly focused on a star topology learning architecture with synchronized (time-triggered) model training rounds, where the local models of the devices are periodically aggregated by a centralized coordinating node. However, in many settings, such a coordinating node may not exist, motivating efforts to fully decentralize FL. In this work, we propose a novel methodology for distributed model aggregations via asynchronous, event-triggered consensus iterations over the network graph topology. We consider heterogeneous communication event thresholds at each device that weigh the change in local model parameters against the available local resources in deciding the benefit of aggregations at each iteration. Through theoretical analysis, we demonstrate that our methodology achieves asymptotic convergence to the globally optimal learning model under standard assumptions in distributed learning and graph consensus literature, and without restrictive connectivity requirements on the underlying topology. Subsequent numerical results demonstrate that our methodology obtains substantial improvements in communication requirements compared with FL baselines.

READ FULL TEXT
research
11/23/2022

Event-Triggered Decentralized Federated Learning over Resource-Constrained Edge Devices

Federated learning (FL) is a technique for distributed machine learning ...
research
09/07/2021

Federated Learning Beyond the Star: Local D2D Model Consensus with Global Cluster Sampling

Federated learning has emerged as a popular technique for distributing m...
research
08/09/2023

Tram-FL: Routing-based Model Training for Decentralized Federated Learning

In decentralized federated learning (DFL), substantial traffic from freq...
research
11/10/2021

DACFL: Dynamic Average Consensus Based Federated Learning in Decentralized Topology

Federated learning (FL) is a burgeoning distributed machine learning fra...
research
12/27/2019

Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks

Federated learning (FL) is emerging as a new paradigm to train machine l...
research
07/18/2020

Multi-Stage Hybrid Federated Learning over Large-Scale Wireless Fog Networks

One of the popular methods for distributed machine learning (ML) is fede...
research
05/20/2020

Consensus Driven Learning

As the complexity of our neural network models grow, so too do the data ...

Please sign up or login with your details

Forgot password? Click here to reset