IEEE

Graph-Based Joint Client Clustering and Resource Allocation for Wireless Distributed Learning: A New Hierarchical Federated Learning Framework With Non-IID Data

Abstract: Hierarchical federated learning (HFL) is a key technology enabling distributed learning with reduced communication overhead. However, practical HFL systems encounter two major challenges: ...
IEEE

Ensemble-Enhanced Semi-Supervised Learning With Optimized Graph Construction for High-Dimensional Data

Abstract: Graph-based methods have demonstrated exceptional performance in semi-supervised classification. However, existing graph-based methods typically construct either a predefined graph in the ...