mlsanityData to 7 Oct 2026

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection

arXiv 2205.10014 ↗First posted 20 May 2022cs.LG cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery. Despite these progresses, how to ensure various deep graph learning algorithms behave in a socially responsible manner and meet regulatory compliance requirements becomes an emerging problem, especially in risk-sensitive domains. Trustworthy graph learning (TwGL) aims to solve the above problems from a technical viewpoint. In contrast to conventional graph learning research which mainly cares about model performance, TwGL considers various reliability and safety aspects of the graph learning framework including but not limited to robustness, explainability, and privacy. In this survey, we provide a comprehensive review of recent leading approaches in the TwGL field from three dimensions, namely, reliability, explainability, and privacy protection. We give a general categorization for existing work and review typical work for each category. To give further insights for TwGL research, we provide a unified view to inspect previous works and build the connection between them. We also point out some important open problems remaining to be solved in the future developments of TwGL.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 112 of its 161 references that are in the map. First posted on arXiv 20 May 2022.

Builds on

112 of 161 references.

References · 112

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2019Invariant Risk Minimizationcited by 1,832
  8. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  9. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  10. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  11. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  12. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
38 more
  1. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  2. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  3. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  4. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  5. 2019Federated Machine Learning: Concept and Applicationscited by 409
  6. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  7. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  8. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  9. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  10. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  11. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
  12. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
  13. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  14. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  15. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  16. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
  17. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
  18. 2019Explainability Techniques for Graph Convolutional Networkscited by 160
  19. 2020Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networkscited by 152
  20. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 152
  21. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  22. 2020Backdoor Attacks to Graph Neural Networkscited by 126
  23. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  24. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  25. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  26. 2021DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networkscited by 117
  27. 2020Stealing Links from Graph Neural Networkscited by 114
  28. 2021Federated Graph Classification over Non-IID Graphscited by 113
  29. 2020Graph Backdoorcited by 112
  30. 2021Robustness of Graph Neural Networks at Scalecited by 100
  31. 2021FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendationcited by 97
  32. 2019Graph Adversarial Training: Dynamically Regularizing Based on Graph Structurecited by 93
  33. 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 91
  34. 2020Quantifying Privacy Leakage in Graph Embeddingcited by 82
  35. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
  36. 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
  37. 2021Membership Inference Attack on Graph Neural Networkscited by 81
  38. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80

50 most cited of 112 All 112 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 11; 2024: 5; 2025: 3.

20 papers.

Sort:

By area:

  1. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  2. 2023Mind the Label Shift of Augmentation-based Graph OOD Generalizationcited by 34
  3. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  4. 2023A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applicationscited by 22
  5. 2024Uncertainty in Graph Neural Networks: A Surveycited by 20
  6. 2023MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentationcited by 18
  7. 2023Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networkscited by 16
  8. 2022TopoImb: Toward Topology-level Imbalance in Learning from Graphscited by 12
  9. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  10. 2023RegExplainer: Generating Explanations for Graph Neural Networks in Regression Taskscited by 9
  11. 2023Combating Bilateral Edge Noise for Robust Link Predictioncited by 9
  12. 2025OpenGU: A Comprehensive Benchmark for Graph Unlearningcited by 8
8 more
  1. 2023Rumor Detection with Diverse Counterfactual Evidencecited by 4
  2. 2023Generative Explanations for Graph Neural Network: Methods and Evaluationscited by 4
  3. 2023When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlookcited by 4
  4. 2024A Survey of Out-of-distribution Generalization for Graph Machine Learning from a Causal Viewcited by 3
  5. 2023Unstructured and structured data: Can we have the best of both worlds with large language models?cited by 2
  6. 2025Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defensescited by 2
  7. 2024Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learningcited by 1
  8. 2025Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Processcited by 0