Federated learning (FL) allows the collaborative training of a collective model by a vast number of decentralized clients while ensuring that these clients’ data remain private and are not shared. In practical situations, the training data utilized in FL often exhibit non-IID characteristics, hence diminishing the efficacy of FL. Our study presents a novel privacy-preserving FL algorithm, HW-DPFL, which leverages data label distribution similarity as a basis for its design. Our proposed approach achieves this objective without incurring any additional overhead communication. In this study, we provide evidence to support the assertion that our approach improves the privacy guarantee and convergence of FL both theoretically and empirically.
Healthcare fraud poses significant risks to insurance systems, undermining both financial sustainability and equitable access to care. Accurate detection of fraudulent claims is therefore critical to ensuring the integrity of healthcare insurance operations. However, the increasing sophistication of fraud techniques and limited data availability have undermined the performance of traditional detection approaches. To address these challenges, this paper proposes WCGAN-GA-RF, an integrated fraud detection framework that synergistically combines Wasserstein Conditional Generative Adversarial Network with gradient penalty (WCGAN-GP) for synthetic data generation, genetic algorithm-based feature selection (GA-RF) for dimensionality reduction, and Random Forest (RF) for classification. The proposed framework was empirically validated on a real-world dataset of 16,000 healthcare insurance claims from a Chinese healthcare technology firm, characterized by a 16:1 class imbalance ratio ( fraudulent samples) and 118 original features. Using a stratified train–test split with results averaged over five independent runs, the WCGAN-GA-RF framework achieved a precision of , a recall of , and an F1-score of . Notably, the GA-RF component achieved a feature reduction (from 80 to 28 features) while maintaining competitive detection accuracy. Comparative experiments demonstrate that the proposed approach outperforms conventional oversampling methods, including Random Oversampling (ROS), Synthetic Minority Oversampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN), particularly in handling high-dimensional, severely imbalanced healthcare fraud data.
The personalized federated averaging algorithm integrates a federated averaging approach with a model-agnostic meta-learning technique. In real-world heterogeneous scenarios, it is essential to implement additional privacy protection techniques for personalized federated learning. We propose a novel differentially private federated meta-learning scheme, CLDP-pFedAvg, which achieves client-level differential privacy guarantees for federated learning involving large heterogeneous clients. The client-level differentially private meta-based FedAvg algorithm enables clients to upload local model parameters for aggregation securely. Furthermore, we provide a convergence analysis of the clipping-enabled differentially private meta-based FedAvg algorithm. The proposed strategy is evaluated across various datasets, and the findings indicate that our approach offers improved privacy protection while maintaining model accuracy.