Reproduce “Unlocking the Specialization Capability of PPG Foundation Models for Wearable Signals through Structured Pruning and Adaptive Fine-Tuning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Huaming Du, Zhixian Xie, Gaoyang Zhen, Gang Kou, Guisong Liu, Yanchao Tan, Wendan Tao, Yuhao Xu and 1 more
SPAFT adapts PPG foundation models by pruning low-importance, redundant filters and selectively fine-tuning paths in the compact network. Across four CNN-based models and evaluated tasks, it achieves the best reported values in 82.8% of regression and 87.5% of classification metric comparisons. These aggregate results are not universal: on Ring-PPG heart-rate estimation, it trails PFEC.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.