# An Adaptive Differentially Private Federated Learning Framework Source: [An Adaptive Differentially Private Federated Learning Framework]() Collection index: [llms.txt]() Data updated: 2026-07-10T05:00:01.277Z Authors: Jin Wang, Hui Ma, Yajun Zhang, Xinjun Pei, Ming Yan, Fei Xing, Yikun Chen Published: 2026-02-06T16:27:33.000Z ## Abstract Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments, device heterogeneity and non-independent and identically distributed (Non-IID) data often lead to unstable and biased gradient. When differential privacy is enforced, conventional fixed gradient clipping and Gaussian noise injection may further amplify gradient perturbations, resulting in training oscillation and degraded model performance. To address these challenges, we propose an adaptive differentially private federated learning framework that explicitly targets model efficiency under heterogeneous and privacy-constrained settings. On the client side, a lightweight local dimensionality reduction module is introduced to learn reduced-dimensional intermediate representations and produce more structured gradients during backpropagation, thereby mitigating noise amplification during local optimization. On the server side, an adaptive gradient clipping strategy dynamically adjusts clipping thresholds based on historical update statistics to avoid over-clipping and noise domination. Furthermore, a constraint-aware robust aggregation mechanism is designed to suppress unreliable or noise-dominated client updates and stabilize global optimization. Extensive experiments on CIFAR-10, SVHN, and STL-10 demonstrate that the proposed method consistently improves convergence stability and classification performance under differential privacy. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CIFAR-10 standard](): Image Classification; CIFAR-10 standard; Accuracy: 81.08. - [Image Classification on SVHN standard](): Image Classification; SVHN standard; Accuracy: 89.74. ## Original sources and implementation [Original paper]() [PDF]()