Beyond federated learning: On confidentiality-critical machine learning applications in industry

W. Zellinger, V. Wieser, M. Kumar, D. Brunner, N. Shepeleva, R. Gálvez, J. Langer, L. Fischer, B. Moser. Beyond federated learning: On confidentiality-critical machine learning applications in industry. volume 180, pages 734-743, DOI 10.1016/j.procs.2021.01.296, 2, 2021.

Autoren
  • Werner Zellinger
  • Volkmar Wieser
  • Mohit Kumar
  • David Brunner
  • Natalia Shepeleva
  • Rafa Gálvez
  • Josef Langer
  • Lukas Fischer
  • Bernhard A. Moser
BuchProcedia Computer Science
TypIn Konferenzband
Band180
DOI10.1016/j.procs.2021.01.296
Monat2
Jahr2021
Seiten734-743
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.