Reproduce “Differentially Private Federated Class-Incremental Learning for EEG Mental State Classification” 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
Baran Can Gül, Ali Gülümser, Nasser Jazdi, Michael Weyrich
FedEEG adapts federated EEG models to learn arriving mental-state labels while retaining earlier classes across five clients. It combines synaptic-intelligence consolidation, local balanced replay, and differential privacy applied only to the classification head. In a nine-round, five-class stream, replay reduces mean forgetting from 0.333 to 0.144, but final accuracy remains near the 20% chance level.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.