FLowDUP generates personalized federated models for unlabeled clients via a hypernetwork operating in a low-dimensional random subspace, with a transductive multi-task PAC-Bayes bound motivating the objective.
All of the above approaches, however, require a client to have labeled data in order to obtain a personalized model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions
FLowDUP generates personalized federated models for unlabeled clients via a hypernetwork operating in a low-dimensional random subspace, with a transductive multi-task PAC-Bayes bound motivating the objective.