Module: tff.learning.algorithms

Libraries providing implementations of federated learning algorithms.

Functions

build_fed_eval(...): Builds a learning process that performs federated evaluation.

build_fed_kmeans(...): Builds a learning process for federated k-means clustering.

build_fed_recon(...): Builds the IterativeProcess for optimization using FedRecon.

build_fed_recon_eval(...): Builds a tff.Computation for evaluating a reconstruction Model.

build_fed_sgd(...): Builds a learning process that performs federated SGD.

build_mime_lite_with_optimizer_schedule(...): Builds a learning process for Mime Lite with optimizer scheduling.

build_personalization_eval_computation(...): Builds the TFF computation for evaluating personalization strategies.

build_unweighted_fed_avg(...): Builds a learning process that performs federated averaging.

build_unweighted_fed_prox(...): Builds a learning process that performs the FedProx algorithm.

build_unweighted_mime_lite(...): Builds a learning process that performs Mime Lite.

build_weighted_fed_avg(...): Builds a learning process that performs federated averaging.

build_weighted_fed_avg_with_optimizer_schedule(...): Builds a learning process for FedAvg with client optimizer scheduling.

build_weighted_fed_prox(...): Builds a learning process that performs the FedProx algorithm.

build_weighted_mime_lite(...): Builds a learning process that performs Mime Lite.