SuPerFed

Implementation of the [SuPerFed22] algorithm.

References

[SuPerFed22]

Seok-Ju Hahn, Minwoo Jeong, and Junghye Lee. Connecting Low-Loss Subspace for Personalized Federated Learning. In KDD (2022). URL: https://arxiv.org/abs/2109.07628v3

Classes included in fluke.algorithms.superfed

SuPerFedClient

SuPerFed

Classes

class fluke.algorithms.superfed.SuPerFedClient(index: int, model: Module, train_set: FastDataLoader, test_set: FastDataLoader, optimizer_cfg: OptimizerConfigurator, loss_fn: Module, local_epochs: int = 3, fine_tuning_epochs: int = 0, clipping: float = 0, mode: str = 'global', start_mix: int = 10, mu: float = 0.1, nu: float = 0.1, **kwargs: dict[str, Any])[source]

Bases: PFLClient

class fluke.algorithms.superfed.SuPerFed(n_clients: int, data_splitter: DataSplitter, hyper_params: DDict | dict[str, Any], **kwargs: dict[str, Any])[source]

Bases: PersonalizedFL