Awesome Trustworthy Graph Neural Networks

A collection of trustworthy graph neural networks methods.

Survey

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability.
Dai E, Zhao T, Zhu H, et al.
Machine Intelligence Research 2024. [pdf]

Uncertainty in Graph Neural Networks: A Survey.
Wang F, Liu Y, Liu K, et al.
Arxiv 2024. [pdf]

Trustworthy Graph Neural Networks: Aspects, Methods and Trends.
Zhang H, Wu B, Yuan X, et al.
Proceedings of the IEEE 2024. [pdf]

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection.
Wu B, Li J, Yu J, et al.
Arxiv 2022. [pdf]

GNN Calibration

Regularization during training

Balanced Confidence Calibration for Graph Neural Networks.
Yang H, Wang M, Wang Q, et al.
KDD 2024. [pdf]

On Calibration of Graph Neural Networks for Node Classification.
Liu T, Liu Y, Hildebrandt M, et al.
ICJNN 2022. [pdf] ↔️ [code]

GCL: Graph Calibration Loss for Trustworthy Graph Neural Networks.
Wang M, Yang H, Cheng Q.
MM 2022. [pdf]

Post-hoc

Calibrating Graph Neural Networks from a Data-centric Perspective.
Yang C, Yang C, Shi C, et al.
WWW 2024. [pdf] ↔️ [code]

Improving GNN Calibration with Discriminative Ability: Insights and Strategies.
Fang Y, Li X, Chen Q, et al.
AAAI 2024. [pdf]

SimCalib: Graph Neural Network Calibration Based on Similarity between Nodes.
Tang B, Wu Z, Wu X, et al.
AAAI 2024. [pdf]

Moderate Message Passing Improves Calibration: A Universal Way to Mitigate Confidence Bias in Graph Neural Networks.
Wang M, Yang H, Huang J, et al.
AAAI 2024. [pdf]

Confidence correction for trained graph convolutional networks.
Yuan J, Guo H, Zhou C, et al.
Pattern Recognition 2024. [pdf]

Towards Reliable Rare Category Analysis on Graphs via Individual Calibration.
Wu L, Lei B, Xu D, et al.
KDD 2023. [pdf] ↔️ [code]

What Makes Graph Neural Networks Miscalibrated?
Hsu H H H, Shen Y, Tomani C, et al.
NeurIPS 2022. [pdf] ↔️ [code]

On Calibration of Graph Neural Networks for Node Classification.
Liu T, Liu Y, Hildebrandt M, et al.
ICJNN 2022. [pdf] ↔️ [code]

Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration.
Wang X, Liu H, Shi C, et al.
NeurIPS 2021. [pdf] ↔️ [code]

Mix-n-match : Ensemble and compositional methods for uncertainty calibration in deep learning.
Zhang J, Kailkhura B, Han T Y J.
ICML 2020. [pdf] ↔️ [code]

On calibration of modern neural networks.
Guo C, Pleiss G, Sun Y, et al.
ICML 2017. [pdf] ↔️ [code]

Uncertainty Estimation VS Quantification

Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification.
Lin X, Zhang W, Shi F, et al.
ICML 2024. [pdf]

Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks.
Trivedi P, Heimann M, Anirudh R, et al.
ICLR 2023. [pdf] ↔️ [code]

Improvements on Uncertainty Quantification for Node Classification via Distance-Based Regularization.
Hart R, Yu L, Lou Y, et al.
NeurIPS 2023. [pdf] ↔️ [code]

Calibrate Automated Graph Neural Network via Hyperparameter Uncertainty.
Yang X, Wang J, Zhao X, et al.
CIKM 2022. [pdf] ↔️ [code]

JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks.
Kang J, Zhou Q, Tong H.
KDD 2022. [pdf] ↔️ [code]

A Graph Is More Than Its Nodes: Towards Structured Uncertainty-Aware Learning on Graphs.
Hsu H H H, Shen Y, Cremers D.
Arxiv 2022. [pdf] ↔️ [code]

Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification.
Stadler M, Charpentier B, Geisler S, et al.
NeurIPS 2021. [pdf] ↔️ [code]

Uncertainty Aware Semi-Supervised Learning on Graph Data.
Zhao X, Chen F, Hu S, et al.
NeurIPS 2020. [pdf] ↔️ [code]

Conformal Prediction

Conformalized Link Prediction on Graph Neural Networks.
Zhao T, Kang J, Cheng L.
KDD 2024. [pdf]

Similarity-Navigated Conformal Prediction for Graph Neural Networks.
Song J, Huang J, Jiang W, et al.
NeurIPS 2024. [pdf]

Conformal Prediction Sets for Graph Neural Networks.
Zargarbashi S H, Antonelli S, Bojchevski A.
ICML 2023. [pdf] ↔️ [code]

Distribution Free Prediction Sets for Node Classification.
Clarkson J.
ICML 2023. [pdf] ↔️ [code]

Uncertainty Quantification over Graph with Conformalized Graph Neural Networks.
Huang K, Jin Y, Candes E, et al.
NeurIPS 2023. [pdf] ↔️ [code]

OOD

Calibrate Graph Neural Networks under Out-of-Distribution Nodes via Deep Q-learning.
Shi W, Yang X, Zhao X, et al.
CIKM 2023. [pdf] ↔️ [code]

GOOD: A Graph Out-of-Distribution Benchmark.
Gui S, Li X, Wang L, et al.
KDD 2022. [pdf] ↔️ [code]

Learning on Graphs with Out-of-Distribution Nodes.
Song Y, Wang D.
KDD 2022. [pdf] ↔️ [code]

Other

Deep Insights into Noisy Pseudo Labeling on Graph Data.
Wang B, Li J, Liu Y, et al.
NeurIPS 2023. [pdf] ↔️ [code]

GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks.
Li Y, Xiong M, Hooi B.
ICML 2023. [pdf] ↔️ [code]