论文标题
使用对抗图像来改善非IID数据的联合学习结果
Using adversarial images to improve outcomes of federated learning for non-IID data
论文作者
论文摘要
联合学习的重要问题之一是如何处理不平衡的数据。该贡献引入了一种新型技术，旨在使用由I-FGSM方法创建的对抗输入来处理标签偏斜的非IID数据。对抗性输入指导培训过程，并允许加权联邦平均，以更重要的是具有“选定”本地标签分布的客户。报告并分析了从图像分类任务，MNIST和CIFAR-10数据集收集的实验结果。
One of the important problems in federated learning is how to deal with unbalanced data. This contribution introduces a novel technique designed to deal with label skewed non-IID data, using adversarial inputs, created by the I-FGSM method. Adversarial inputs guide the training process and allow the Weighted Federated Averaging to give more importance to clients with 'selected' local label distributions. Experimental results, gathered from image classification tasks, for MNIST and CIFAR-10 datasets, are reported and analyzed.
