FedIL: Federated Incremental Learning from Decentralized Unlabeled Data with Convergence Analysis

no code implementations • 23 Feb 2023 • Nan Yang, Dong Yuan, Charles Z Liu, Yongkun Deng, Wei Bao

Most existing federated learning methods assume that clients have fully labeled data to train on, while in reality, it is hard for the clients to get task-specific labels due to users' privacy concerns, high labeling costs, or lack of expertise.

Federated Learning Incremental Learning +1