Feature-Based Machine Unlearning for Vertical Federated Learning in IoT Networks
IEEE Transactions on Mobile Computing · 2025-06 · 24 (6) · 5031-5044
DOI: 10.1109/tmc.2025.3530529 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2025-06. Verfasst von Zijie Pan und 6 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: Natural Science Foundation for Young Scientists of Shanxi Province, Postdoctoral Fellowship Program of CPSF, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
In the era of the Internet of Things (IoT), managing the deluge of data generated by distributed devices presents unique challenges, particularly concerning privacy and the efficient use of computational resources. Vertical Federated Learning (VFL) offers a promising avenue for collaborative machine learning without centralizing data, thereby addressing privacy concerns inherent in traditional approaches. However, as data privacy laws and personal data deletion requests become more prevalent, the necessity for effective machine unlearning strategies within VFL frameworks grows increasingly important. To this end, this paper introduces a novel approach to feature-based machine unlearning tailored specifically for VFL systems in IoT networks. Our methodology enables the selective removal of data influence from trained models without the need for full retraining, thus preserving model utility while ensuring compliance with privacy requirements. By integrating a combination of feature relevance measuring techniques and efficient communication protocols, our solution minimizes the data footprint on network nodes, reduces bandwidth consumption, and maintains the integrity and performance of the learning models. To the best of our knowledge, our proposed framework represents the first practical approach to enable machine unlearning within vertical federated learning environments. We demonstrate the effectiveness of our approach through rigorous evaluation using several IoT datasets, highlighting significant improvements in unlearning efficiency and model robustness compared to existing techniques. Our work not only furthers the development of sustainable and compliant machine learning models in IoT but also sets a foundational framework for future research in secure and efficient data management within federated environments.
Förderung
- Natural Science Foundation for Young Scientists of Shanxi Province
- Postdoctoral Fellowship Program of CPSF
- China Postdoctoral Science Foundation
- Fundo para o Desenvolvimento das Ciências e da Tecnologia
- General R&D Subsidy Program
- NSFC-FDCT
- Joint Scientific Research Project Fund
- Guangzhou University Research Project
Zitieren
APA
Pan, Z., Ying, Z., Wang, Y., Zhang, C., Zhang, W., Zhou, W., & Zhu, L. (2025). Feature-Based Machine Unlearning for Vertical Federated Learning in IoT Networks. IEEE Transactions on Mobile Computing, 24(6), 5031-5044. https://doi.org/10.1109/tmc.2025.3530529
Vancouver
Pan Z, Ying Z, Wang Y, Zhang C, Zhang W, Zhou W, et al. Feature-Based Machine Unlearning for Vertical Federated Learning in IoT Networks. IEEE Transactions on Mobile Computing. 2025;24(6):5031-5044. doi:10.1109/tmc.2025.3530529
BibTeX
@article{Pan2025,
author = {Pan, Zijie and Ying, Zuobin and Wang, Yajie and Zhang, Chuan and Zhang, Weiting and Zhou, Wanlei and Zhu, Liehuang},
title = {Feature-Based Machine Unlearning for Vertical Federated Learning in IoT Networks},
journal = {IEEE Transactions on Mobile Computing},
year = {2025},
volume = {24},
number = {6},
pages = {5031--5044},
doi = {10.1109/tmc.2025.3530529}
}
EUVIMED