Federated Learning based on Self-Evolving Gaussian Clustering

2025-08-21

AI Summary

To address the limitations of conventional clustering in federated learning—namely, the requirement of pre-specifying the number of clusters and poor adaptability to non-IID data—this paper proposes a self-evolving federated fuzzy clustering framework. The method integrates federated learning with a self-evolving Gaussian fuzzy system: each client dynamically generates and merges Gaussian membership functions locally, while cluster evolution is guided by overlap-based criteria, enabling fully distributed clustering without prior knowledge of cluster count. Clients upload only model parameters—preserving data privacy—while the global server supports structural, adaptive expansion during aggregation. Experiments on multiple UCI datasets demonstrate significant improvements in both classification and clustering performance over baseline methods, particularly under severe non-IID conditions, with enhanced robustness and generalizability. Although computational overhead is moderately increased, the trade-off yields substantially improved practical utility and model adaptability.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

Abstract

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.

Problem

• Dynamically determines cluster count without prior specification
• Enables decentralized model training without sharing raw data
• Outperforms traditional methods on UCI classification tasks

Innovation

• Federated Learning with dynamic cluster adaptation
• Local model training without data sharing
• Self-evolving Gaussian clustering without predefined clusters