The development of highly sophisticated neural networks has allowed for fast progress in every field of computer vision, however, applications where annotated data is prohibited due to privacy or security concerns remain challenging. Federated Learning (FL) offers a promising framework for individuals aiming to collaboratively develop a shared model while preserving data privacy. Nevertheless, our findings reveal that variations in data distribution among clients can profoundly affect FL methodologies, primarily due to instabilities in the aggregation process. We also propose a novel FL framework to mitigate the adverse effects of covariate shifts among federated clients by combining individual parameter pruning and regularization techniques to improve the robustness of individual clients' models to aggregate. Each client's model is optimized through magnitude-based pruning and the addition of dropout and noise injection layers to build more resilient decision pathways in the networks and improve the robustness of the model's parameter aggregation step. The proposed framework is capable of extracting robust representations even in the presence of very large covariate shifts among client data distributions and in the federation of a small number of clients. Empirical findings substantiate the effectiveness of our proposed methodology across common benchmark datasets, including CIFAR10, MNIST, SVHN, and Fashion MNIST. Furthermore, we introduce the CelebA-Gender dataset, specifically designed to evaluate performance on a more realistic domain. The proposed method is capable of extracting robust representations even in the presence of both high and low covariate shifts among client data distributions.

翻译：高度复杂的神经网络的发展推动了计算机视觉各个领域的快速进步，然而，由于隐私或安全问题而无法获取标注数据的应用场景仍然具有挑战性。联邦学习（FL）为希望在保护数据隐私的同时协作开发共享模型的个体提供了一个有前景的框架。然而，我们的研究发现，客户端之间数据分布的差异会深刻影响FL方法，这主要归因于聚合过程中的不稳定性。我们提出了一种新颖的FL框架，通过结合个体参数剪枝和正则化技术来减轻联邦客户端间协变量偏移的不利影响，从而提高个体客户端模型在聚合时的鲁棒性。每个客户端的模型通过基于幅度的剪枝以及添加Dropout和噪声注入层进行优化，以在网络中构建更具弹性的决策路径，并提升模型参数聚合步骤的鲁棒性。即使在客户端数据分布存在极大协变量偏移以及联邦客户端数量较少的情况下，所提出的框架也能够提取鲁棒的表征。实证结果证实了我们所提方法在包括CIFAR10、MNIST、SVHN和Fashion MNIST在内的常见基准数据集上的有效性。此外，我们引入了CelebA-Gender数据集，该数据集专门设计用于在更现实的领域上评估性能。即使在客户端数据分布同时存在高和低协变量偏移的情况下，所提出的方法也能够提取鲁棒的表征。