FedGPA: a multi-level aggregation framework for federated learning with collaborative optimization of generalization and personalization

A federated learning framework for Non-IID data : data feature optimization and personalization strategy

Federated learning is an emerging distributed machine learning paradigm that enables multiple edge devices to collaboratively train task-specific models while preserving data privacy. However, the non-independent and identically distributed nature of client data often leads to client drift, slow convergence, and degrad...

FedACC: personalized federated learning via adaptive parameter decoupling and client-side clustering

Review on Aggregation Frameworks For High-Performance Federated Learning

This work establishes the research direction toward an adaptive weighted aggregation framework in which client contributions are dynamically adjusted using multiple performance-related indicators, expected to improve global accuracy, convergence stability, fairness, minority-class representation, and robustness to low-...

Robust federated learning aggregation for highly heterogeneous data

Personalized Private-Shared Federated Model with an Application to Distributed Additive Manufacturing

Currently, many small and medium-sized organizations struggle with limited data availability and computational resources, leading to poor predictive capabilities due to data isolation. Federated Learning (FL) addresses this by enabling collaborative model training without data sharing, overcoming data silos. However, F...

Latent Information Sharing for Accelerating Federated Learning

Federated learning (FL) is a communication-efficient distributed learning paradigm. However, client drift remains one of the most critical challenges, hindering the efficient training of a global model. In this study, we propose a novel latent information sharing scheme that directly mitigates data heterogeneity across...