mlsanityData to 7 Oct 2026

GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks

arXiv 2410.09570 ↗First posted 12 Oct 2024cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks deliver strong classification results but often suffer from poor calibration performance, leading to overconfidence or underconfidence. This is particularly problematic in high stakes applications where accurate uncertainty estimates are essential. Existing post hoc methods, such as temperature scaling, fail to effectively utilize graph structures, while current GNN calibration methods often overlook the potential of leveraging diverse input information and model ensembles jointly. In the paper, we propose Graph Ensemble Temperature Scaling, a novel calibration framework that combines input and model ensemble strategies within a Graph Mixture of Experts archi SOTA calibration techniques, reducing expected calibration error by 25 percent across 10 GNN benchmark datasets. Additionally, GETS is computationally efficient, scalable, and capable of selecting effective input combinations for improved calibration performance. The implementation is available via Github.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 12 Oct 2024.

Builds on

34 of 54 references.

References · 34

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
  10. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  11. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  12. 2019Graph Neural Networks for Social Recommendationcited by 711
22 more
  1. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  2. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  3. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 359
  4. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  5. 2019Verified Uncertainty Calibrationcited by 307
  6. 2020Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learningcited by 190
  7. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 91
  8. 2020Inductive Graph Neural Networks for Spatiotemporal Krigingcited by 90
  9. 2023Uncertainty Quantification over Graph with Conformalized Graph Neural Networkscited by 79
  10. 2020Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantificationcited by 77
  11. 2022Better Uncertainty Calibration via Proper Scores for Classification and Beyondcited by 65
  12. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 63
  13. 2022What Makes Graph Neural Networks Miscalibrated?cited by 39
  14. 2022Uncovering the Structural Fairness in Graph Contrastive Learningcited by 29
  15. 2022RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Networkcited by 27
  16. 2019Are Graph Neural Networks Miscalibrated?cited by 14
  17. 2014Binary Classifier Calibration: Non-parametric approachcited by 13
  18. 2022MBCT: Tree-Based Feature-Aware Binning for Individual Uncertainty Calibrationcited by 11
  19. 2021Online Calibrated and Conformal Prediction Improves Bayesian Optimizationcited by 10
  20. 2023SimCalib: Graph Neural Network Calibration based on Similarity between Nodescited by 10
  21. 2024SAUC: Sparsity-Aware Uncertainty Calibration for Spatiotemporal Prediction with Graph Neural Networkscited by 4
  22. 2022Uncertainty Calibration in Bayesian Neural Networks via Distance-Aware Priorscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scalingcited by 2
  2. 2026When does distribution shift break graph neural networks calibration?cited by 0
  3. 2026HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibrationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment
  2. 2025Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study
  3. 2024Graph-based Confidence Calibration for Large Language Models
  4. 2026Toward Calibrated Mixture-of-Experts Under Distribution Shift
  5. 2025Rethinking Calibration for Early-Exit Neural Networks
  6. 2024Calibrating Language Models with Adaptive Temperature Scaling
  7. 2024Acceleration Algorithms in GNNs: A Survey
  8. 2022Efficient Graph Neural Network Inference at Large Scale