Implement Custom FL Strategy

I want to implement an FL algorithm and run it like flower-simulation-step-by-step-pytorch. Therefore, I have to change the strategy from the line 55 to 78 in the file. Suppose my strategy name is FedNew. What steps should I follow to do this type of strategy implementation? If there is any example code available please share.

Thank you

Hi @ruhul5347, you could customise a new strategy (e.g., inherited from FedAvg) as below:

class FedNew(flwr.server.strategy.FedAvg):
    def __init__(**kwargs: Any,)
        # define any new arguments

    def aggregate_fit(
        server_round: int,
        results: List[Tuple[ClientProxy, FitRes]],
        failures: List[Union[Tuple[ClientProxy, FitRes], BaseException]],
    ) -> Tuple[Optional[Parameters], Dict[str, Scalar]]:
        # define new aggregation methods here

    def configure_fit(
        self, rnd: int, parameters: Parameters, client_manager: ClientManager
    ) -> List[Tuple[ClientProxy, FitIns]]:
        # override client sampling method if needed

Note that aggregate_fit() and configure_fit() are for training. If doing changes for evaluation, then override aggregate_evaluate() and configure_evaluate().

Then, call this new FedNew strategy similar to line 68 in
strategy = FedNew(...)