Graph data is present everywhere and has vast ranging applications from finding the common interests of people to the optimization of road traffic. Due to the interconnectedness of nodes in graphs, training neural networks on graphs can be done in two settings: in transductive learning, the model can have access to the test features in the training phase; in the inductive setting, the test data remains unseen. We explore the differences between inductive and transductive learning on real citation networks when the graphs are converted to undirected graphs. We find that the models achieve better accuracy in the transductive setting than in the inductive setting, but that the gap between validation and test accuracy is also higher, which indicates the models trained in an inductive setting have better generalization capabilities.