Reproduce “Federated deep transfer learning for EEG decoding using multiple BCI tasks” 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
Xiaoxi Wei, A. Aldo Faisal
MF-SCSN tackles EEG data fragmentation across sites by keeping raw recordings, feature extractors, labels, and predictions local while sharing learned features through a common network. In a BEETL test of five subjects and 1,000 trials, it achieved 51.2% weighted accuracy versus 48.2% for a target-only shallow-ConvNet baseline. The comparison does not isolate the gain’s source or establish privacy guarantees.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.