In this work, we show that popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) do not model and cannot learn a class of general neighborhood mixing relationships. To address this weakness, we propose a new model, MixHop, that can capture these difference relationships by learning mixed feature representations of neighbors at various distances. MixHop requires no additional memory or computational complexity, and outperforms challenging baselines on several graph datasets. In addition, we propose a sparsity regularization that allows us to visualize how the network prioritizes neighborhood information across different graph datasets. Our analysis of the learned parameters reveals that different datasets utilize neighborhood mixing in different ways