3 papers
cs.LG2026
Towards Performance-Enhanced Model-Contrastive Federated Learning using Historical Information in Heterogeneous Scenarios
Hongliang Zhang, Jiguo Yu, Guijuan Wang +4
Federated Learning (FL) enables multiple nodes to collaboratively train a model without sharing raw data. However, FL systems are usually deployed in heterogeneous scenarios, where…
cs.DC2025
DFPL: Decentralized Federated Prototype Learning Across Heterogeneous Data Distributions
Hongliang Zhang, Fenghua Xu, Zhongyuan Yu +3
Federated learning is a distributed machine learning paradigm through centralized model aggregation. However, standard federated learning relies on a centralized server, making it…
cs.CR2025
PPFPL: Cross-silo Privacy-preserving Federated Prototype Learning Against Data Poisoning Attacks
Hongliang Zhang, Jiguo Yu, Fenghua Xu +5
Privacy-Preserving Federated Learning (PPFL) enables multiple clients to collaboratively train models by submitting secreted model updates. Nonetheless, PPFL is vulnerable to data…