Work

FedPLA: Cross-Silo Federated Learning with Proximal Regularization and Loss-Aware Aggregation

Year: 2026

Type: article

Abstract: Cross-silo Federated Learning (FL) allows organizations to train models collaboratively while keeping data local, but performance often suffers under Non-IID data due to clients' diverse, domain-specific datasets. While existing work explores client-side personalization and server-side adaptivity separately, and some recent methods attempt to combine them, they often rely on complex optimization or static similarity measures, limiting their and robustness. We propose FedPLA, a cross-silo FL approach that explicitly integrates both perspectives. On the client side, FedPLA applies composite regularization to personalized heads, combining a proximal term for stability with L2 regularization to reduce overfitting. On the server side, a loss-aware aggregation adaptively adjusts global step sizes based on system loss dynamics, enhancing convergence under Non-IID data. Experiments on FMNIST, CIFAR-10, CIFAR-100, and a real-world power system dataset show that FedPLA consistently surpasses FL methods.

Source: IEICE Transactions on Information and Systems

DOI: 10.1587/transinf.2025edl8060

Authors: Huayang ZHANG, Lingyu LIANG, Shuangping HUANG, Tingwen YU, Ting YU

Institutions: South China University of Technology, China Southern Power Grid (China)

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funders: Guangzhou Municipal Science and Technology Project, National Key Research and Development Program of China, Basic and Applied Basic Research Foundation of Guangdong Province

Awards: G520475613, G7660411463