:py:mod:`kosmos.ml.fl.fl_server`
================================

.. py:module:: kosmos.ml.fl.fl_server







Classes
-------

.. py:class:: FLServer(trainer: kosmos.ml.sl_trainer.SLTrainer, node: kosmos.topology.node.Node)


   Federated learning server.

   Initialize a federated learning server.

   :param trainer: The trainer used by this server.
   :type trainer: SLTrainer
   :param node: The node representing this server in the topology.
   :type node: Node





   |

   .. rubric:: Methods

   .. py:method:: get_model_state() -> dict

      Get the current model state of the server.

      :returns: A state_dict containing the model parameters.
      :rtype: dict


   .. py:method:: aggregate(client_states: list[dict]) -> None

      Aggregate model states from clients using simple averaging.

      :param client_states: A list of model state_dicts from clients.
      :type client_states: list[dict]


   .. py:method:: test(dataloader: torch.utils.data.DataLoader) -> kosmos.ml.sl_result.SLTestIterationResult

      Evaluate the global model on test data.

      :param dataloader: Dataloader providing the test data.
      :type dataloader: DataLoader

      :returns: The result of the test iteration.
      :rtype: SLTestIterationResult