Privacy in Multimodal Federated Human Activity Recognition
Abstract
Human Activity Recognition (HAR) training data is often privacy-sensitive or held by non-cooperative entities. Federated Learning (FL) addresses such concerns by training ML models on edge clients. This work studies the impact of privacy in federated HAR at a user, environment, and sensor level. We show that the performance of FL for HAR depends on the assumed privacy level of the FL system and primarily upon the colocation of data from different sensors. By avoiding data sharing and assuming privacy at the human or environment level, as prior works have done, the accuracy decreases by 5-7%. However, extending this to the modality level and strictly separating sensor data between multiple clients may decrease the accuracy by 19-42%. As this form of privacy is necessary for the ethical utilisation of passive sensing methods in HAR, we implement a system where clients mutually train both a general FL model and a group-level one per modality. Our evaluation shows that this method leads to only a 7-13% decrease in accuracy, making it possible to build HAR systems with diverse hardware.
Cite
@article{arxiv.2305.12134,
title = {Privacy in Multimodal Federated Human Activity Recognition},
author = {Alex Iacob and Pedro P. B. Gusmão and Nicholas D. Lane and Armand K. Koupai and Mohammud J. Bocus and Raúl Santos-Rodríguez and Robert J. Piechocki and Ryan McConville},
journal= {arXiv preprint arXiv:2305.12134},
year = {2023}
}
Comments
In 3rd On-Device Intelligence Workshop at MLSys 2023, 8 pages