BFLP: An Adaptive Federated Learning Framework for Internet of Vehicles

Algorithm 2

Horizontal federated learning: VehicleUpdate (k, ).

Input: DB_vehicle

Output:

 1: ⟵(split DB_vehicle into batches of size G); //G is local minibatch size of vehicle.

 2: for each local epoch i from 1 to I_vehicle is the number of local epochs.

 3:  for batch do

 4:   ⟵ − η∇l (; b);

 5:  end for

 6:  Use CPC to encrypt ;

 7:  return to the base station

 8: end for