Crossing Domain Borders with Federated Few-Shot Adaptation

Manuel Röder, Maximilian Münch, Christoph Raab, Frank-Michael Schleif

2024

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-trained 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.

Paper Citation

in Harvard Style

Röder M., Münch M., Raab C. and Schleif F. (2024). Crossing Domain Borders with Federated Few-Shot Adaptation. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 511-521. DOI: 10.5220/0012351900003654

in Bibtex Style

@conference{icpram24,
author={Manuel Röder and Maximilian Münch and Christoph Raab and Frank-Michael Schleif},
title={Crossing Domain Borders with Federated Few-Shot Adaptation},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={511-521},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012351900003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Crossing Domain Borders with Federated Few-Shot Adaptation
SN - 978-989-758-684-2
AU - Röder M.
AU - Münch M.
AU - Raab C.
AU - Schleif F.
PY - 2024
SP - 511
EP - 521
DO - 10.5220/0012351900003654
PB - SciTePress