Uncertainty in Graph Neural Networks: A Survey

arXiv:2403.07185v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) have been extensively used in various real-world applications. However, the predictive uncertainty of GNNs stemming from diverse sources such as inherent randomness in data and model training errors can lead to unstable and erroneous predictions. Therefore, identifying, quantifying, and utilizing uncertainty are essential to enhance the performance of the model for the downstream tasks as well as the reliability of the GNN predictions. This survey aims to provide a comprehensive overview …

abstract applications arxiv cs.lg data diverse errors gnns graph graph neural networks however networks neural networks predictions predictive randomness stat.ml stemming survey training type uncertainty world