Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond. (arXiv:2309.00416v1 [cs.LG])

Federated learning (FL) is a framework for training machine learning models
in a distributed and collaborative manner. During training, a set of
participating clients process their data stored locally, sharing only the model
updates obtained by minimizing a cost function over their local inputs. FL was
proposed as a stepping-stone towards privacy-preserving machine learning, but
it has been shown vulnerable to issues such as leakage of private information,
lack of personalization of the model, and the possibility of having a …

beyond clients cost data distributed fairness federated learning framework function inputs local locally machine machine learning machine learning models privacy process sharing training updates