Reproduce “PULSE: Personalized Opportunistic Learning for Wearable Devices” 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
Mattia Giovanni Campana, Dariush Salami, Hüseyin Yiğitler, Stephan Sigg
PULSE enables selective collaboration between wearable devices adapting personalized models to changing users and sensors. It chooses whether to contact a reachable peer, then accepts the peer’s learning signal only when its gradient agrees with the local gradient. In simulated cross-dataset human-activity recognition, it outperforms local-only training in dense-contact cases while completing fewer peer-assisted updates, but results do not establish energy savings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.