Label synchronization for Hybrid Federated Learning in manufacturing and predictive maintenance

Label synchronization for Hybrid Federated Learning in manufacturing and predictive maintenance

Llasag Rosero, Raúl (University of Coimbra, Centre for Informatics and System)
Silva, Catarina (University of Coimbra, Centre for Informatics and System)
Ribeiro, Bernardete (University of Coimbra, Centre for Informatics and System)
Santos, Bruno F. (TU Delft Air Transport & Operations)

2024

Artificial Intelligence (AI) is transforming the future of industries by introducing new paradigms. To address data privacy and other challenges of decentralization, research has focused on Federated Learning (FL), which combines distributed Machine Learning (ML) models from multiple parties without exchanging confidential information. However, conventional FL methods struggle to handle situations where data samples have diverse features and sizes. We propose a Hybrid Federated Learning solution with label synchronization to overcome this challenge. Our FedLabSync algorithm trains a feed-forward Artificial Neural Network while alerts that it can aggregate knowledge of other ML architectures compatible with the Stochastic Gradient Descent algorithm by conducting a penalized collaborative optimization. We conducted two industrial case studies: product inspection in Bosch factories and aircraft component Remaining Useful Life predictions. Our experiments on decentralized data scenarios demonstrate that FedLabSync can produce a global AI model that achieves results on par with those of centralized learning methods.

Artificial Neural Network
Federated Learning
Hybrid Federated Learning
Machine Learning
Stochastic Gradient Descent

http://resolver.tudelft.nl/uuid:e16bfa00-f7c2-4cf8-a815-abb0d54257f6

https://doi.org/10.1007/s10845-023-02298-8

0956-5515

Journal of Intelligent Manufacturing

Institutional Repository

journal article

© 2024 Raúl Llasag Rosero, Catarina Silva, Bernardete Ribeiro, Bruno F. Santos