A Federated Learning Approach to Breast Cancer Prediction in a Collaborative Learning Framework

. 2023 Dec 17;11(24):3185. doi: 10.3390/healthcare11243185

Algorithm 2 Global Model Training

1:
Input: List of client models $[{C l i e n t}_{1}, {C l i e n t}_{2}, \dots, {C l i e n t}_{N}]$
2:
Input: Number of clients N
3:
Output: Global federated model $F e d e r a t e d_M o d e l$
4:
Initialize an empty list $p r e d i c t i o n s$
5:
for $i \leftarrow 1$ to N do
6:
${p r e d i c t i o n s}_{i} \leftarrow {C l i e n t}_{i} . p r e d i c t (X)$ ▹ Make predictions on validation data
7:
$p r e d i c t i o n s . a p p e n d ({p r e d i c t i o n s}_{i})$ ▹ Aggregate predictions
8:
end for
9:
$c o m b i n e d_p r e d i c t i o n s \leftarrow s u m (p r e d i c t i o n s)$ ▹ Sum predictions across clients
10:
$f i n a l_p r e d i c t i o n s \leftarrow a r g m a x (c o m b i n e d_p r e d i c t i o n s)$ ▹ Select class with the highest probability
11:
Initialize the global federated model $F e d e r a t e d M o d e l$
12:
Return $F e d e r a t e d M o d e l$