DWLR: Domain Adaptation under Label Shift for Wearable Sensor
Published in IJCAI, 2024
Wearable-sensor models face distribution shifts across users and devices, including changes in both features and class proportions. DWLR addresses these two shifts together through learnable label-distribution reweighting, information-gain regularization, and separate alignment in the time and frequency domains. Across three wearable-sensor datasets, the method improves average performance by 5.85% over prior approaches.
Recommended citation: Juren Li, Yang Yang, Youmin Chen, Jianfeng Zhang, Zeyu Lai, and Lujia Pan. DWLR: Domain Adaptation under Label Shift for Wearable Sensor. IJCAI 2024.
Download Paper