FedBP

The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.The dataset is divided into five training batches and one test batch, each with 10000 images. The test batch contains exactly 1000 randomly-selected images from each class. The training batches contain the remaining images in random order, but some training batches may contain more images from one class than another. Between them, the training batches contain exactly 5000 images from each class.The WISDM dataset is a public dataset for Human Activity Recognition (HAR). It contains sensor data collected from smartphones and smartwatches that are used to recognize many different human activities.Our federated learning robustness experiments on these two datasets.

CIFAR-10数据集由60000张32×32的彩色图像组成，分为10个类别，每个类别6000张图像。其中训练图像50000张，测试图像10000张。该数据集被划分为5个训练批次和1个测试批次，每个批次包含10000张图像。测试批次恰好包含每个类别中随机选取的1000张图像。训练批次包含剩余的图像，顺序随机，但部分训练批次可能某一类别的图像数量多于其他类别。整体而言，训练批次中每个类别恰好包含5000张图像。WISDM数据集是用于人类活动识别（Human Activity Recognition, HAR）的公共数据集，包含从智能手机和智能手表收集的传感器数据，这些数据用于识别多种不同的人类活动。我们在这两个数据集上进行了联邦学习鲁棒性实验。