Federated Learning based on Self-Evolving Gaussian Clustering
This addresses the need for adaptive clustering in decentralized data processing for federated learning applications, though it appears incremental with computational intensity noted.
The paper tackles the problem of determining cluster numbers in federated learning by introducing a self-evolving Gaussian clustering method that dynamically adapts to new clusters without requiring pre-specified numbers. The results show it outperforms established classification methods on several UCI datasets.
In this study, we present an Evolving Fuzzy System within the context of Federated Learning, which adapts dynamically with the addition of new clusters and therefore does not require the number of clusters to be selected apriori. Unlike traditional methods, Federated Learning allows models to be trained locally on clients' devices, sharing only the model parameters with a central server instead of the data. Our method, implemented using PyTorch, was tested on clustering and classification tasks. The results show that our approach outperforms established classification methods on several well-known UCI datasets. While computationally intensive due to overlap condition calculations, the proposed method demonstrates significant advantages in decentralized data processing.