Authors:
Manuel Röder
1
;
Maximilian Münch
2
;
Christoph Raab
3
and
Frank-Michael Schleif
1
Affiliations:
1
Faculty of Computer Science and Business Information Systems, Technical University of Applied Sciences Würzburg-Schweinfurt, Würzburg, Germany
;
2
Department of Computer Science, University of Groningen, Groningen, Netherlands
;
3
IAV GmbH, Berlin, Germany
Keyword(s):
Federated Learning, Domain Adaptation, Few-Shot Learning, Deep Transfer Learning, Resource Constraints, Sporadic Model Updates.
Abstract:
Federated Learning has gained significant attention as a data protecting paradigm for decentralized, client-side learning in the era of interconnected, sensor-equipped edge devices. However, practical applications of Federated Learning face three major challenges: First, the expensive data labeling process required for target adaptation involves human participation. Second, the data collection process on client devices suffers from covariate shift due to environmental impact on attached sensors, leading to a discrepancy between source and target samples. Third, in resource-limited environments, both continuous or regular model updates are often infeasible due to limited data transmission capabilities or technical constraints on channel availability and energy efficiency. To address these challenges, we propose FedAcross, an efficient and scalable Federated Learning framework designed specifically for real-world client adaptation in industrial environments. It is based on a pre-traine
d source model that includes a deep backbone, an adaptation module, and a classifier running on a powerful server. By freezing the backbone and the classifier during client adaptation on resource-constrained devices, we enable the domain adaptive linear layer to solely handle target domain adaptation and minimize the overall computational overhead. Our extensive experimental results validate the effectiveness of FedAcross in achieving competitive adaptation on low-end client devices with limited target samples, effectively addressing the challenge of domain shift. Our framework effectively handles sporadic model updates within resource-limited environments, ensuring practical and seamless deployment.
(More)