Federated Learning Based on OPTICS Clustering Optimization

Table 1

Summary of symbols.

Symbol	Explanation
	Number of clients
M	Number of data generating distribution
frac	The fraction of clients that perform computation on each round
B	The local minibatch size used for the client updates
β	The local minibatch
E	The number of local epochs
η	Learning rate
	Neural network parameterization
Dk	Data on client k
	Model weight on clients k
ci∈C	One cluster in the set of all clusters found by OCFL