Text-Enhanced Data-free Approach for Federated Class-Incremental Learning

arXiv:2403.14101v1 Announce Type: cross
Abstract: Federated Class-Incremental Learning (FCIL) is an underexplored yet pivotal issue, involving the dynamic addition of new classes in the context of federated learning. In this field, Data-Free Knowledge Transfer (DFKT) plays a crucial role in addressing catastrophic forgetting and data privacy problems. However, prior approaches lack the crucial synergy between DFKT and the model training phases, causing DFKT to encounter difficulties in generating high-quality data from a non-anchored latent space of the old task model. …

arxiv class cs.cl cs.cv cs.lg data free incremental text type