The integration of Federated Learning (FL) into manufacturing represents a transformative approach to harnessing distributed data while preserving privacy. This special session aims to explore cutting-edge methods, applications, and challenges associated with the implementation of FL in industrial settings.

Bringing together researchers and practitioners, the session addresses topics such as collaborative model training across multiple manufacturing units, dealing with data heterogeneity, ensuring data security, and enhancing applications such as predictive maintenance with FL. Discussions will also cover the role of FL in Industry 4.0, with an emphasis on human-centric and sustainable manufacturing processes.
Topics of Interest

Topics include, but are not limited to:

Applications of FL in Industry 4.0 (predictive maintenance, manufacturing optimization, quality inspection)
Data privacy and security challenges in FL
Data heterogeneity and device heterogeneity in FL
Resource-efficient FL systems for production lines
Theoretical contributions to FL in manufacturing
Explainable FL models for manufacturing processes
Federated Reinforcement Learning applications
Federated datasets for industry-relevant FL benchmarks
FL deployment architectures for industrial environments
Communication-efficient FL for constrained factory floor networks