WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scaling
- URL: http://arxiv.org/abs/2506.23782v2
- Date: Tue, 08 Jul 2025 12:34:43 GMT
- Title: WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scaling
- Authors: Xiaoyang Li, Linwei Tao, Haohui Lu, Minjing Dong, Junbin Gao, Chang Xu,
- Abstract summary: We propose Wavelet-Aware Temperature Scaling (WATS), a post-hoc calibration framework that assigns node-specific temperatures based on graph wavelet features.<n>WATS harnesses the scalability and topology sensitivity of graph wavelets to refine confidence estimates, all without retraining or access to neighboring logits or predictions.
- Score: 43.23012871829196
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Graph Neural Networks (GNNs) have demonstrated strong predictive performance on relational data; however, their confidence estimates often misalign with actual predictive correctness, posing significant limitations for deployment in safety-critical settings. While existing graph-aware calibration methods seek to mitigate this limitation, they primarily depend on coarse one-hop statistics, such as neighbor-predicted confidence, or latent node embeddings, thereby neglecting the fine-grained structural heterogeneity inherent in graph topology. In this work, we propose Wavelet-Aware Temperature Scaling (WATS), a post-hoc calibration framework that assigns node-specific temperatures based on tunable heat-kernel graph wavelet features. Specifically, WATS harnesses the scalability and topology sensitivity of graph wavelets to refine confidence estimates, all without necessitating model retraining or access to neighboring logits or predictions. Extensive evaluations across seven benchmark datasets with varying graph structures and two GNN backbones demonstrate that WATS achieves the lowest Expected Calibration Error (ECE) among all compared methods, outperforming both classical and graph-specific baselines by up to 42.3\% in ECE and reducing calibration variance by 17.24\% on average compared with graph-specific methods. Moreover, WATS remains computationally efficient, scaling well across graphs of diverse sizes and densities. Code will be released based on publication.
Related papers
- Non-exchangeable Conformal Prediction for Temporal Graph Neural Networks [11.01716974299811]
Conformal prediction for graph neural networks (GNNs) offers a promising framework for quantifying uncertainty.<n>Existing methods predominantly focus on static graphs, neglecting the evolving nature of real-world graphs.<n>We introduce NCPNET, a novel end-to-end conformal prediction framework tailored for temporal graphs.
arXiv Detail & Related papers (2025-07-02T21:15:00Z) - GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks [8.505932176266368]
Graph Neural Networks deliver strong classification results but often suffer from poor calibration performance.<n>Existing post hoc methods, such as temperature scaling, fail to effectively utilize graph structures.<n>We propose Graph Ensemble Temperature Scaling, a novel calibration framework that combines input and model ensemble strategies.
arXiv Detail & Related papers (2024-10-12T15:34:41Z) - Learning to Reweight for Graph Neural Network [63.978102332612906]
Graph Neural Networks (GNNs) show promising results for graph tasks.
Existing GNNs' generalization ability will degrade when there exist distribution shifts between testing and training graph data.
We propose a novel nonlinear graph decorrelation method, which can substantially improve the out-of-distribution generalization ability.
arXiv Detail & Related papers (2023-12-19T12:25:10Z) - Graph Out-of-Distribution Generalization with Controllable Data
Augmentation [51.17476258673232]
Graph Neural Network (GNN) has demonstrated extraordinary performance in classifying graph properties.
Due to the selection bias of training and testing data, distribution deviation is widespread.
We propose OOD calibration to measure the distribution deviation of virtual samples.
arXiv Detail & Related papers (2023-08-16T13:10:27Z) - Uncertainty Quantification over Graph with Conformalized Graph Neural
Networks [52.20904874696597]
Graph Neural Networks (GNNs) are powerful machine learning prediction models on graph-structured data.
GNNs lack rigorous uncertainty estimates, limiting their reliable deployment in settings where the cost of errors is significant.
We propose conformalized GNN (CF-GNN), extending conformal prediction (CP) to graph-based models for guaranteed uncertainty estimates.
arXiv Detail & Related papers (2023-05-23T21:38:23Z) - What Makes Graph Neural Networks Miscalibrated? [48.00374886504513]
We conduct a systematic study on the calibration qualities of graph neural networks (GNNs)
We identify five factors which influence the calibration of GNNs: general under-confident tendency, diversity of nodewise predictive distributions, distance to training nodes, relative confidence level, and neighborhood similarity.
We design a novel calibration method named Graph Attention Temperature Scaling (GATS), which is tailored for calibrating graph neural networks.
arXiv Detail & Related papers (2022-10-12T16:41:42Z) - On Calibration of Graph Neural Networks for Node Classification [29.738179864433445]
Graph neural networks learn entity and edge embeddings for tasks such as node classification and link prediction.
These models achieve good performance with respect to accuracy, but the confidence scores associated with the predictions might not be calibrated.
We propose a topology-aware calibration method that takes the neighboring nodes into account and yields improved calibration.
arXiv Detail & Related papers (2022-06-03T13:48:10Z) - Line Graph Neural Networks for Link Prediction [71.00689542259052]
We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications.
In this formalism, a link prediction problem is converted to a graph classification task.
We propose to seek a radically different and novel path by making use of the line graphs in graph theory.
In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task.
arXiv Detail & Related papers (2020-10-20T05:54:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.