Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection
For researchers in wearable health monitoring, this work offers a lightweight personalization approach that avoids costly fine-tuning or pre-training, though the gains are incremental over existing methods.
The paper tackles personalization in wearable stress detection by proposing a retrieval-augmented method that uses frozen foundation models to retrieve similar patterns from a user's history, achieving +3.92% accuracy and +4.76% macro F1-score over a non-personalized baseline on the WESAD dataset without requiring labeled user data.
Personalization in wearable-based stress detection remains challenging due to substantial inter-individual variability in physiological and behavioral responses. While traditional approaches rely on user-specific fine-tuning or costly self-supervised pre-training on large datasets, we propose a lightweight alternative based on retrieval-augmented personalization. Our method leverages frozen, out-of-domain foundation models to retrieve similar patterns from a target user's history and encode them into a compact personalized embedding that modulates representations extracted by a lightweight transformer network. We evaluate our approach on the WESAD stress detection dataset with N=15 users, comprising wrist-worn physiological (EDA, BVP, temperature) and activity (accelerometer) signals, and report gains of +3.92\% in accuracy and +4.76\% in macro F1-score over a non-personalized transformer baseline, approaching supervised fine-tuning performance without requiring any labeled user data. We further show that temporal retrieval, where only prior user samples are available, achieves performance close to full intra-user retrieval, demonstrating robustness to limited user history. Finally, we explore personalization in a cross-dataset retrieval setting, leveraging embeddings from the K-Emocon dataset to personalize representations for stress detection on the WESAD dataset.