Towards Efficient Replay in Federated Incremental Learning

arXiv:2403.05890v1 Announce Type: new
Abstract: In Federated Learning (FL), the data in each client is typically assumed fixed or static. However, data often comes in an incremental manner in real-world applications, where the data domain may increase dynamically. In this work, we study catastrophic forgetting with data heterogeneity in Federated Incremental Learning (FIL) scenarios where edge clients may lack enough storage space to retain full data. We propose to employ a simple, generic framework for FIL named Re-Fed, which can …

abstract applications arxiv catastrophic forgetting client cs.dc cs.lg data domain federated learning however incremental study type work world