Federat\textbf{T}ed Cl\textbf{A}ss Continual Lea\textbf{R}nin\textbf{G

Federated Class Continual Learning (FCCL) addresses the challenge of training machine learning models on a stream of data from multiple sources (federated learning) where new classes are introduced incrementally (continual learning), without catastrophic forgetting of previously learned information. Current research focuses on developing efficient algorithms and model architectures, such as those based on transformers, autoencoders, and spiking neural networks, that minimize communication overhead and data storage while maintaining accuracy across tasks. This field is significant because it enables the development of robust and adaptable AI systems for real-world applications with continuously evolving data streams, particularly in privacy-sensitive settings like healthcare and personalized recommendations.