Industrial Federated Learning -- Requirements and System Design
This addresses the challenge of adapting federated learning for industrial applications, which is incremental as it builds on existing FL methods by adding cohort-based evaluation.
The paper tackles the problem of applying federated learning to industrial settings where data similarity assumptions are often violated due to variations in machine types and conditions, by introducing an Industrial Federated Learning system that organizes tasks into cohorts based on data similarity to optimize collaboration and prevent negative knowledge transfer.
Federated Learning (FL) is a very promising approach for improving decentralized Machine Learning (ML) models by exchanging knowledge between participating clients without revealing private data. Nevertheless, FL is still not tailored to the industrial context as strong data similarity is assumed for all FL tasks. This is rarely the case in industrial machine data with variations in machine type, operational- and environmental conditions. Therefore, we introduce an Industrial Federated Learning (IFL) system supporting knowledge exchange in continuously evaluated and updated FL cohorts of learning tasks with sufficient data similarity. This enables optimal collaboration of business partners in common ML problems, prevents negative knowledge transfer, and ensures resource optimization of involved edge devices.