AINeutralarXiv – CS AI · 10h ago6/10
🧠
From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity
Researchers propose FEAT, a federated learning method that improves continual learning by addressing class imbalance and representation collapse across distributed clients. The approach combines geometric alignment and energy-based correction to better utilize exemplar samples while maintaining performance under dynamic heterogeneity.