Enhancing Fairness in Federated Learning: A Contribution-Based Differentiated Model Approach

Algorithm 1

Clustering algorithm based on contribution.

	Input: contribution scores set , number of clusters
	Output: clustering results
(1)	Randomly select a sample from as the first cluster center.
(2)	fordo
(3)	Calculate the shortest distance between each sample and the existing cluster centers .
(4)	Select the next cluster center with probability .
(5)	end for
(6)	Use the selected cluster centers as initial cluster centers, i.e., .
(7)	while The cluster centers no longer change do
(8)	For each sample , calculate its distance to each cluster center , where .
(9)	Assign each sample to the cluster of nearest cluster center .
(10)	fordo
(11)	Calculate the mean of all samples in cluster .
(12)	update the cluster center
(13)	end for
(14)	end while
(15)	Output clustering results