INNER CODE UNIT · Python
total_w
Tisha-runwal/Personalized-Federated-Learning-for-Privacy--Preserving-and-Scalable-IoT-Driven-Smart-Healthcare · pfl_hcare/fl/server.py:263
total_w = sum(all_weights)
norm_w = [w / total_w for w in all_weights]
aggregated_tensors = secure_agg.aggregate(tensor_params, norm_w)
global_params = [t.numpy() for t in aggregated_tensors]
encryption_report = secure_agg.get_report()
else:
# ---------------------------------------------------------------
# Step 5b: Plain FedAvg aggregation (Eq.1) for non-pfl_hcare methods
# ---------------------------------------------------------------
total_w = sum(all_weights)
norm_w = [w / total_w for w in all_weights]
n_tensors = len(all_client_params[0])
new_global: list[np.ndarray] = []
for pidx in range(n_tensors):
weighted = sum(
nw * all_client_params[ci][pidx]
for ci, nw in enumerate(norm_w)
)