Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Resource-Constrained On-Device Learning by Dynamic Averaging

: Heppe, Lukas; Kamp, Michael; Adilova, Linara; Heinrich, Danny; Piatkowski, Nico; Morik, Katharina


Koprinska, Irena:
ECML PKDD 2020 Workshops. Proceedings : Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020, Ghent, Belgium, September 14-18, 2020
Cham: Springer Nature, 2020 (Communications in computer and information science 1323)
ISBN: 978-3-030-65964-6 (Print)
ISBN: 978-3-030-65965-3 (Online)
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) <2020, Online>
Workshop on Parallel, Distributed and Federated Learning (PDFL) <2020, Online>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
01-S18038A/B/C; ML2R
Fraunhofer IAIS ()

The communication between data-generating devices is partially responsible for a growing portion of the worlds power consumption. Thus reducing communication is vital, both, from an economical and an ecological perspective. For machine learning, on-device learning avoids sending raw data, which can reduce communication substantially. Furthermore, not centralizing the data protects privacy-sensitive data. However, most learning algorithms require hardware with high computation power and thus high energy consumption. In contrast, ultra-low-power processors, like FPGAs or micro-controllers, allow for energy-efficient learning of local models. Combined with communication-efficient distributed learning strategies, this reduces the overall energy consumption and enables applications that were yet impossible due to limited energy on local devices. The major challenge is then, that the low-power processors typically only have integer processing capabilities. This paper investigates an approach to communication-efficient on-device learning of integer exponential families that can be executed on low-power processors, is privacy-preserving, and effectively minimizes communication. The empirical evaluation shows that the approach can reach a model quality comparable to a centrally learned regular model with an order of magnitude less communication. Comparing the overall energy consumption, this reduces the required energy for solving the machine learning task by a significant amount.