AI RESEARCH
C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning
arXiv CS.LG
•
ArXi:2509.19674v2 Announce Type: replace Federated continual learning (FCL) tackles scenarios of learning from continuously emerging task data across distributed clients, where the key challenge lies in addressing both temporal forgetting over time and spatial forgetting simultaneously. Recently, prompt-based FCL methods have shown advanced performance through task-wise prompt communication. In this study, we underscore that the existing prompt-based FCL methods are prone to class-wise knowledge coherence between prompts across clients.