FedPAC: A Federated Semi-Supervised Learning Approach for Non-IID Data with Feature Shift

Federated Semi-Supervised Learning (FSSL) enables collaborative model training across distributed clients with limited labeled data while preserving data privacy. However, a critical challenge in FSSL is feature shift, where clients exhibit diverse feature distributions despite sharing the same task. To address this issue, we propose FedPAC, a novel FSSL framework that integrates Contrastive Mean-Teacher Regularization and Perturbation-Aware Gradient Descent. Our framework enhances feature representation learning by aligning feature distributions between teacher and student models and mitigates optimization challenges caused by feature heterogeneity through controlled gradient perturbations. Extensive experiments on benchmark datasets demonstrate that FedPAC outperforms existing FSSL methods in feature shift scenarios, making it a practical solution for real-world applications such as medical imaging and industrial fault diagnosis.