FedHUG: Federated Heterogeneous Unsupervised Generalization for Remote Physiological Measurements
This addresses privacy and labeling challenges in remote physiological measurements, offering a federated learning solution for heterogeneous unsupervised domain generalization.
The paper tackles the problem of updating real-world deployed models for remote physiological measurements without labeled client data, proposing the FedHUG framework which shows superior performance across state-of-the-art techniques using RGB video or mmWave radar.
Remote physiological measurement gained wide attention, while it requires collecting users' privacy-sensitive information, and existing contactless measurements still rely on labeled client data. This presents challenges when we want to further update real-world deployed models with numerous user data lacking labels. To resolve these challenges, we instantiate a new protocol called Federated Unsupervised Domain Generalization (FUDG) in this work. Subsequently, the \textbf{Fed}erated \textbf{H}eterogeneous \textbf{U}nsupervised \textbf{G}eneralization (\textbf{FedHUG}) framework is proposed and consists of: (1) Minimal Bias Aggregation module dynamically adjusts aggregation weights based on prior-driven bias evaluation to cope with heterogeneous non-IID features from multiple domains. (2) The Global Distribution-aware Learning Controller parameterizes the label distribution and dynamically manipulates client-specific training strategies, thereby mitigating the server-client label distribution skew and long-tail issue. The proposal shows superior performance across state-of-the-art techniques in estimation with either RGB video or mmWave radar. The code will be released.