Graph neural networks (GNNs) have been widely applied to network related tasks in recent years. The core idea of GNNs is neighborhood aggregation where nodes in a network can learn adequate representations by aggregating the information from their neighbors. Despite the great success of GNNs, few studies investigate how different types of structure of the network based data affect the performance of GNNs in completing network related tasks. In this work, we study the performance of GNNs for different types of network structure at different homophily levels.