Under non-independent and identically distributed (Non-IID) conditions, significant variations exist in local model updates across clients and training phases during the collaborative modeling process of differential privacy federated learning (DP-FL). Fixed clipping thresholds and noise scales struggle to accommodate these diverse update differences, leading to mismatches between local update intensity and noise perturbations. This imbalance results in data privacy leaks and suboptimal model accuracy. To address this, we propose a differential privacy federated learning method based on adaptive clipping thresholds. During each communication round, the server adaptively estimates the global clipping threshold for that round using a quantile strategy based on the statistical distribution of client update norms. Simultaneously, clients adaptively adjust their noise scales according to the clipping threshold magnitude, enabling dynamic matching of clipping intensity and noise perturbation across training phases and clients. The novelty of this work lies in a quantile-driven, round-wise global clipping adaptation that synchronizes sensitivity bounding and noise calibration across heterogeneous clients, enabling improved privacy–utility behavior under a fixed privacy accountant. Using experimental results on the rail damage datasets, our proposed method slightly reduces the attacker’s MIA ROC-AUC by 0.0033 and 0.0080 compared with Fed-DPA and DP-FedAvg, respectively, indicating stronger privacy protection, while improving average accuracy by 1.55% and 3.35% and achieving faster, more stable convergence. We further validate its effectiveness on CIFAR-10 under non-IID partitions.

Federated Learning (FL) enables collaborative model training without sharing raw data, offering a promising solution for privacy-sensitive applications. However, in real-world deployments, significant disparities in client computational capabilities lead to imbalanced model updates, resulting in slow convergence and degraded model generalization. To address this challenge, this paper proposes a novel federated aggregation optimization method, FedAWR, which features adaptive adjustment of learning rates and weights. Specifically, during the global aggregation phase, our method dynamically adjusts each client’s aggregation weight based on its computational capability and configures an appropriate learning rate to balance training progress. Experiments on multi-classification tasks using the Steel Rail Defect and CIFAR-10 datasets demonstrate that the proposed method exhibits significant advantages over mainstream federated algorithms in both convergence efficiency and model generalization performance, thereby validating its effectiveness and superiority.

As federated learning scales up in distributed scenarios, training instability and performance degradation caused by data quality issues—such as statistical heterogeneity and noise—have become major bottlenecks for practical deployment. Existing aggregation algorithms have been shown to not adequately account for differences in data importance. This can exacerbate client selection bias and incentive misalignment. As a result, global convergence can slow down and performance can deteriorate. To address this issue, this paper proposes a robust federated learning framework based on data heterogeneity grading and marginal contribution calculation. The objective of this study is to enhance the overall performance of federated learning systems in heterogeneous environments by quantifying data importance. The framework first grades and quantifies the heterogeneity of client data distributions, precisely characterizing data importance while reducing the computational space for Shapley value calculations, effectively lowering its exponential complexity. Subsequently, it integrates client marginal contributions with data distribution heterogeneity to establish a dynamic weighted aggregation mechanism that balances fairness, robustness, and differentiated data quality requirements. Multi-dataset comparative experiments demonstrate that the proposed method achieves consistent gains in model accuracy and convergence under non-IID splits and noisy-label settings.