Bandwidth Allocation with Device Partitioning for Federated Learning over Industrial IoT networks
arXiv:2605.30892v1 Announce Type: new Abstract: We consider a federated learning (FL) system in which Industrial Internet-of-Things (IIoT) devices collaboratively train a global model over wireless channels without sharing local data. In such systems, communication time is a primary bottleneck that constrains overall training efficiency. Unlike conventional networks that prioritize individual quality-of-service requirements, FL systems collectively aim to converge to an optimal global model as efficiently as possible, which calls for a fundamentally different approach to bandwidth allocation.
The proliferation of Industrial IoT devices and the increasing demand for on-device AI drive the need for efficient federated learning communication strategies right now.
Optimizing federated learning in IIoT environments can significantly accelerate model convergence and improve the practical deployment of AI in industrial settings, impacting efficiency and automation.
This research proposes a new approach to bandwidth allocation, shifting from individual QoS to system-wide FL efficiency, which could fundamentally alter how IIoT AI deployments are engineered.
- · Industrial IoT manufacturers
- · AI model developers
- · Smart factory operators
- · Telecommunication companies
- · Legacy communication protocols
- · Inefficient FL systems
Improved training efficiency and faster deployment of AI models across industrial IoT environments.
Accelerated adoption of AI in manufacturing, logistics, and critical infrastructure due to reduced communication bottlenecks.
Enhanced automation and predictive maintenance leading to significant operational cost reductions and productivity gains across industrial sectors, possibly impacting labor markets.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG