Abstract
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.
Original language | English |
---|---|
Number of pages | 20 |
Journal | Journal of Intelligent Manufacturing |
DOIs | |
Publication status | Published - 2024 |
Funding
This work was partially supported by: (1) The Portuguese Foundation for Science and Technology (FCT) under the project grant FRH/BD/07344/2020, (2) The H2020 KYKLOS 4.0 Project No. 872570 and the H2020 ReMAP Project No. 769288, which the European Commission funds, and (3) The Intelligent Systems Associate Laboratory of the Center of Informatics and Systems of the University of Coimbra CISUC/LASI.Keywords
- Artificial Neural Network
- Federated Learning
- Hybrid Federated Learning
- Machine Learning
- Stochastic Gradient Descent