FedDistill: Global Model Distillation for Local Model De-Biasing in Non-IID Federated Learning

arXiv:2404.09210v1 Announce Type: new
Abstract: Federated Learning (FL) is a novel approach that allows for collaborative machine learning while preserving data privacy by leveraging models trained on decentralized devices. However, FL faces challenges due to non-uniformly distributed (non-iid) data across clients, which impacts model performance and its generalization capabilities. To tackle the non-iid issue, recent efforts have utilized the global model as a teaching mechanism for local models. However, our pilot study shows that their effectiveness is constrained by imbalanced …

abstract arxiv challenges collaborative cs.ai cs.cv cs.lg data data privacy decentralized devices distillation distributed federated learning global however impacts machine machine learning model distillation novel performance privacy type