<ul><li>Recent advancements in graph neural networks (GNNs) have highlighted the critical need of calibrating model predictions, with neighborhood prediction similarity recognized as a pivotal component.</li><li>Existing approaches incorporate neighborhood similarity into node-wise temperature scaling techniques, but this assumption does not hold universally and can lead to sub-optimal calibration.</li><li>The new approach called Simi-Mailbox categorizes nodes by both neighborhood similarity and their own confidence, allowing fine-grained calibration using group-specific temperature scaling.</li><li>Extensive experiments demonstrate the effectiveness of Simi-Mailbox, achieving up to 13.79% error reduction compared to uncalibrated GNN predictions.</li></ul>

Towards Precise Prediction Uncertainty in GNNs: Refining GNNs with Topology-grouping Strategy

Discover more