Federated machine learning frameworks, which take into account confidentiality of distributed data sources are of increasing interest in smart manufacturing. However, the scope of applicability of most such frameworks is restricted in industrial settings due to limitations in the assumptions on the data sources involved. In this work, first, we shed light on the nature of this arising gap between current federated learning and requirements in industrial settings. Our discussion aims at clarifying related notions in emerging sub-disciplines of machine learning, which are partially overlapping. Second, we envision a new confidentiality-preserving approach for smart manufacturing applications based on the more general setting of transfer learning, and envision its implementation in a module-based platform.
%0 Journal Article
%1 ZELLINGER2021734
%A Zellinger, Werner
%A Wieser, Volkmar
%A Kumar, Mohit
%A Brunner, David
%A Shepeleva, Natalia
%A Gálvez, Rafa
%A Langer, Josef
%A Fischer, Lukas
%A Moser, Bernhard
%D 2021
%J Procedia Computer Science
%K beyond federated industry ism learning scch
%P 734-743
%R https://doi.org/10.1016/j.procs.2021.01.296
%T Beyond federated learning: On confidentiality-critical machine learning applications in industry
%U https://www.sciencedirect.com/science/article/pii/S1877050921003458
%V 180
%X Federated machine learning frameworks, which take into account confidentiality of distributed data sources are of increasing interest in smart manufacturing. However, the scope of applicability of most such frameworks is restricted in industrial settings due to limitations in the assumptions on the data sources involved. In this work, first, we shed light on the nature of this arising gap between current federated learning and requirements in industrial settings. Our discussion aims at clarifying related notions in emerging sub-disciplines of machine learning, which are partially overlapping. Second, we envision a new confidentiality-preserving approach for smart manufacturing applications based on the more general setting of transfer learning, and envision its implementation in a module-based platform.
@article{ZELLINGER2021734,
abstract = {Federated machine learning frameworks, which take into account confidentiality of distributed data sources are of increasing interest in smart manufacturing. However, the scope of applicability of most such frameworks is restricted in industrial settings due to limitations in the assumptions on the data sources involved. In this work, first, we shed light on the nature of this arising gap between current federated learning and requirements in industrial settings. Our discussion aims at clarifying related notions in emerging sub-disciplines of machine learning, which are partially overlapping. Second, we envision a new confidentiality-preserving approach for smart manufacturing applications based on the more general setting of transfer learning, and envision its implementation in a module-based platform.},
added-at = {2023-05-09T12:04:34.000+0200},
author = {Zellinger, Werner and Wieser, Volkmar and Kumar, Mohit and Brunner, David and Shepeleva, Natalia and Gálvez, Rafa and Langer, Josef and Fischer, Lukas and Moser, Bernhard},
biburl = {https://www.bibsonomy.org/bibtex/2689d0fc43a00fb20cf0715e9ca8e6035/scch},
doi = {https://doi.org/10.1016/j.procs.2021.01.296},
interhash = {f5b9f22b77d577194d46d019b20c029b},
intrahash = {689d0fc43a00fb20cf0715e9ca8e6035},
issn = {1877-0509},
journal = {Procedia Computer Science},
keywords = {beyond federated industry ism learning scch},
note = {Proceedings of the 2nd International Conference on Industry 4.0 and Smart Manufacturing (ISM 2020)},
pages = {734-743},
timestamp = {2023-05-09T12:04:34.000+0200},
title = {Beyond federated learning: On confidentiality-critical machine learning applications in industry},
url = {https://www.sciencedirect.com/science/article/pii/S1877050921003458},
volume = 180,
year = 2021
}