Graph Neural Networks Use Graphs When They Shouldn't

arXiv:2309.04332v2 Announce Type: replace
Abstract: Predictions over graphs play a crucial role in various domains, including social networks and medicine. Graph Neural Networks (GNNs) have emerged as the dominant approach for learning on graph data. Although a graph-structure is provided as input to the GNN, in some cases the best solution can be obtained by ignoring it. While GNNs have the ability to ignore the graph- structure in such cases, it is not clear that they will. In this work, …

abstract arxiv cases cs.ai cs.lg data domains gnn gnns graph graph data graph neural networks graphs medicine networks neural networks predictions role social social networks solution type