Federated Unlearning for Human Activity Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914741936455680 |
|---|---|
| author | Chen, Kongyang zhang, Dongping Chai, Yaping Zhang, Weibin Wang, Shaowei Shen, Jiaxing |
| author_facet | Chen, Kongyang zhang, Dongping Chai, Yaping Zhang, Weibin Wang, Shaowei Shen, Jiaxing |
| contents | The rapid evolution of Internet of Things (IoT) technology has spurred the widespread adoption of Human Activity Recognition (HAR) in various daily life domains. Federated Learning (FL) is frequently utilized to build a global HAR model by aggregating user contributions without transmitting raw individual data. Despite substantial progress in user privacy protection with FL, challenges persist. Regulations like the General Data Protection Regulation (GDPR) empower users to request data removal, raising a new query in FL: How can a HAR client request data removal without compromising other clients' privacy? In response, we propose a lightweight machine unlearning method for refining the FL HAR model by selectively removing a portion of a client's training data. Our method employs a third-party dataset unrelated to model training. Using KL divergence as a loss function for fine-tuning, we aim to align the predicted probability distribution on forgotten data with the third-party dataset. Additionally, we introduce a membership inference evaluation method to assess unlearning effectiveness. Experimental results across diverse datasets show our method achieves unlearning accuracy comparable to \textit{retraining} methods, resulting in speedups ranging from hundreds to thousands. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03659 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Federated Unlearning for Human Activity Recognition Chen, Kongyang zhang, Dongping Chai, Yaping Zhang, Weibin Wang, Shaowei Shen, Jiaxing Machine Learning Cryptography and Security The rapid evolution of Internet of Things (IoT) technology has spurred the widespread adoption of Human Activity Recognition (HAR) in various daily life domains. Federated Learning (FL) is frequently utilized to build a global HAR model by aggregating user contributions without transmitting raw individual data. Despite substantial progress in user privacy protection with FL, challenges persist. Regulations like the General Data Protection Regulation (GDPR) empower users to request data removal, raising a new query in FL: How can a HAR client request data removal without compromising other clients' privacy? In response, we propose a lightweight machine unlearning method for refining the FL HAR model by selectively removing a portion of a client's training data. Our method employs a third-party dataset unrelated to model training. Using KL divergence as a loss function for fine-tuning, we aim to align the predicted probability distribution on forgotten data with the third-party dataset. Additionally, we introduce a membership inference evaluation method to assess unlearning effectiveness. Experimental results across diverse datasets show our method achieves unlearning accuracy comparable to \textit{retraining} methods, resulting in speedups ranging from hundreds to thousands. |
| title | Federated Unlearning for Human Activity Recognition |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2404.03659 |