Impact of Structure of Network Based Data on Performance of Graph Neural Networks

Graph neural networks (GNNs) have been widely applied to network related tasks in recent years, including node classification, link prediction, community detection, etc. 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 di fferent types of structure of the network based data, such as random networks, smallworld networks, and scale-free networks, a ffect the performance of GNNs in completing network related tasks. Moreover, recent studies have pointed out that the homophily of labels is one of the key properties that influence the performance of GNNs. In this work, we study the performance of GNNs for di fferent types of network structure at di fferent homophily levels. Comprehensive simulations on synthetic networks show the considerable impact of network structure and homophily on the performance of GNNs in terms of prediction e ffectiveness in node classification tasks. The findings of this work emphasize the necessary consideration of network structure of datasets in designing reliable GNNs so that the performance of these GNNs will not deviate due to structural change of the underlined data.