AI RESEARCH
Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings
arXiv CS.LG
•
ArXi:2606.00426v1 Announce Type: new Federated continual learning (FCL) lets distributed clients adapt language-model heads to evolving NLP tasks without sharing raw text. Under user-level differential privacy (DP), replay-based continual learning faces a structural obstacle: clients can release only small noisy lists of candidate replay summaries, and those lists are unordered across clients. We