
FedCLASS, a novel federated class-incremental learning method, mitigates catastrophic forgetting by harmonizing new class scores with the outputs of historical models during self-distillation.


coremsg

federated-class-incremental-learning-with-new-class-augmented-self-distillation-mitigating-catastrophic-forgetting-in-expanding-data-and-class-environments


Federated Class-Incremental Learning with New-Class Augmented Self-Distillation: Mitigating Catastrophic Forgetting in Expanding Data and Class Environments


title_rewrite


FedProK leverages prototypical feature as a novel representation of knowledge to perform spatial-temporal knowledge transfer, enabling trustworthy federated class-incremental learning by overcoming catastrophic forgetting and data heterogeneity.


trustworthy-federated-class-incremental-learning-via-prototypical-feature-knowledge-transfer


Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfer
