Towards Precise Prediction Uncertainty in GNNs: Refining GNNs with Topology-grouping Strategy
This addresses calibration issues in GNNs for applications requiring reliable uncertainty estimates, but it is incremental as it builds on existing temperature scaling techniques.
The paper tackles the problem of inaccurate calibration in graph neural networks (GNNs) by showing that existing methods based on neighborhood similarity are insufficient, and introduces Simi-Mailbox, a method that groups nodes by both similarity and confidence for fine-grained temperature scaling, achieving up to 13.79% error reduction.
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. Existing studies suggest that nodes with analogous neighborhood prediction similarity often exhibit similar calibration characteristics. Building on this insight, recent approaches incorporate neighborhood similarity into node-wise temperature scaling techniques. However, our analysis reveals that this assumption does not hold universally. Calibration errors can differ significantly even among nodes with comparable neighborhood similarity, depending on their confidence levels. This necessitates a re-evaluation of existing GNN calibration methods, as a single, unified approach may lead to sub-optimal calibration. In response, we introduce **Simi-Mailbox**, a novel approach that categorizes nodes by both neighborhood similarity and their own confidence, irrespective of proximity or connectivity. Our method allows fine-grained calibration by employing *group-specific* temperature scaling, with each temperature tailored to address the specific miscalibration level of affiliated nodes, rather than adhering to a uniform trend based on neighborhood similarity. Extensive experiments demonstrate the effectiveness of our **Simi-Mailbox** across diverse datasets on different GNN architectures, achieving up to 13.79\% error reduction compared to uncalibrated GNN predictions.