# Are Graph Neural Networks Miscalibrated?

arXiv: https://arxiv.org/abs/1905.02296 · HTML: https://mlsanity.com/paper/1905.02296/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2019.

## Built on by (most cited first, 14 of 14)

- [Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration](https://mlsanity.com/paper/2109.14285/) (2021)
- [What Makes Graph Neural Networks Miscalibrated?](https://mlsanity.com/paper/2210.06391/) (2022)
- [SimCalib: Graph Neural Network Calibration based on Similarity between Nodes](https://mlsanity.com/paper/2312.11858/) (2023)
- [On Calibration of Graph Neural Networks for Node Classification](https://mlsanity.com/paper/2206.01570/) (2022)
- [A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphs](https://mlsanity.com/paper/2210.15575/) (2022)
- [On the Temperature of Bayesian Graph Neural Networks for Conformal Prediction](https://mlsanity.com/paper/2310.11479/) (2023)
- [Uncertainty Quantification on Graph Learning: A Survey](https://mlsanity.com/paper/2404.14642/) (2024)
- [GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks](https://mlsanity.com/paper/2410.09570/) (2024)
- [In-n-Out: Calibrating Graph Neural Networks for Link Prediction](https://mlsanity.com/paper/2403.04605/) (2024)
- [Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement](https://mlsanity.com/paper/2505.01766/) (2025)
- [CoG: a Two-View Co-training Framework for Defending Adversarial Attacks on Graph](https://mlsanity.com/paper/2109.05558/) (2021)
- [Efficient quantification on large-scale networks](https://mlsanity.com/paper/2503.15267/) (2025)
- [Set Twister for Single-hop Node Classification](https://mlsanity.com/paper/2112.09752/) (2021)
- [HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration](https://mlsanity.com/paper/2609.32426/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have proven to be successful in many classification tasks, outperforming previous state-of-the-art methods in terms of accuracy. However, accuracy alone is not enough for high-stakes decision making. Decision makers want to know the likelihood that a specific GNN prediction is correct. For this purpose, obtaining calibrated models is essential. In this work, we perform an empirical evaluation of the calibration of state-of-the-art GNNs on multiple datasets. Our experiments show that GNNs can be calibrated in some datasets but also badly miscalibrated in others, and that state-of-the-art calibration methods are helpful but do not fix the problem.