mlsanityData to 14 Oct 2026

Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels

arXiv 2201.00232 ↗First posted 1 Jan 2022cs.LGcited by 63

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have shown their great ability in modeling graph structured data. However, real-world graphs usually contain structure noises and have limited labeled nodes. The performance of GNNs would drop significantly when trained on such graphs, which hinders the adoption of GNNs on many applications. Thus, it is important to develop noise-resistant GNNs with limited labeled nodes. However, the work on this is rather limited. Therefore, we study a novel problem of developing robust GNNs on noisy graphs with limited labeled nodes. Our analysis shows that both the noisy edges and limited labeled nodes could harm the message-passing mechanism of GNNs. To mitigate these issues, we propose a novel framework which adopts the noisy edges as supervision to learn a denoised and dense graph, which can down-weight or eliminate noisy edges and facilitate message passing of GNNs to alleviate the issue of limited labeled nodes. The generated edges are further used to regularize the predictions of unlabeled nodes with label smoothness to better train GNNs. Experimental results on real-world datasets demonstrate the robustness of the proposed framework on noisy graphs with limited labeled nodes.

Key facts. Cited by 63 papers in the map (data through 14 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 1 Jan 2022.

Builds on

35 of 47 references.

References · 35

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  7. 2017Neural Collaborative Filteringcited by 1,111
  8. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  9. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  10. 2020Simple and Deep Graph Convolutional Networkscited by 860
  11. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  12. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
23 more
  1. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  2. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  3. 2019Multi-Label Image Recognition with Graph Convolutional Networkscited by 322
  4. 2016Learning Convolutional Neural Networks for Graphscited by 314
  5. 2018Adversarial Attack on Graph Structured Datacited by 301
  6. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  7. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  8. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  9. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  10. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  11. 2020A Semi-supervised Graph Attentive Network for Financial Fraud Detectioncited by 151
  12. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147
  13. 2019Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labelscited by 111
  14. 2020Self-supervised Learning on Graphs: Deep Insights and New Directioncited by 108
  15. 2019Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systemscited by 107
  16. 2014The Rise of Social Botscited by 96
  17. 2020DeepRobust: A PyTorch Library for Adversarial Attacks and Defensescited by 78
  18. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  19. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  20. 2019Transferring Robustness for Graph Neural Network Against Poisoning Attackscited by 58
  21. 2020Self-Supervised Graph Representation Learning via Global Context Predictioncited by 38
  22. 2020Self-supervised Training of Graph Convolutional Networkscited by 24
  23. 2021Semi-Supervised Graph-to-Graph Translationcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 8; 2023: 17; 2024: 19; 2025: 10; 2026: 9.

63 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  2. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 62
  3. 2023Unnoticeable Backdoor Attacks on Graph Neural Networkscited by 45
  4. 2023Cooperative Graph Neural Networkscited by 36
  5. 2024GraphEdit: Large Language Models for Graph Structure Learningcited by 33
  6. 2022Robust Training of Graph Neural Networks via Noise Governancecited by 29
  7. 2022Exploring Edge Disentanglement for Node Classificationcited by 23
  8. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  9. 2023Learning on Graphs under Label Noisecited by 22
  10. 2024Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspectivecited by 22
  11. 2023MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentationcited by 18
  12. 2024Subgraph Pooling: Tackling Negative Transfer on Graphscited by 17
38 more
  1. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  2. 2022GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networkscited by 14
  3. 2023A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacycited by 14
  4. 2022Towards Faithful and Consistent Explanations for Graph Neural Networkscited by 13
  5. 2023RDGSL: Dynamic Graph Representation Learning with Structure Learningcited by 13
  6. 2024Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directionscited by 13
  7. 2022MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distributioncited by 11
  8. 2023ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerancecited by 11
  9. 2022Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attackcited by 10
  10. 2023Regularly Truncated M-estimators for Learning with Noisy Labelscited by 8
  11. 2024Self-Guided Robust Graph Structure Refinementcited by 8
  12. 2024LOGIN: A Large Language Model Consulted Graph Neural Network Training Frameworkcited by 8
  13. 2024LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generationcited by 8
  14. 2024GraphAgent: Agentic Graph Language Assistantcited by 8
  15. 2023Reinforcement Neighborhood Selection for Unsupervised Graph Anomaly Detectioncited by 7
  16. 2024Robustness Inspired Graph Backdoor Defensecited by 7
  17. 2025Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapsecited by 7
  18. 2023Faithful and Consistent Graph Neural Network Explanations with Rationale Alignmentcited by 6
  19. 2023Similarity Preserving Adversarial Graph Contrastive Learningcited by 6
  20. 2024Mitigating Label Noise on Graph via Topological Sample Selectioncited by 6
  21. 2024Toward Structure Fairness in Dynamic Graph Embedding: A Trend-aware Dual Debiasing Approachcited by 6
  22. 2024Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learningcited by 6
  23. 2023OpenGDA: Graph Domain Adaptation Benchmark for Cross-network Learningcited by 5
  24. 2023Certifiably Robust Graph Contrastive Learningcited by 5
  25. 2023Robust Graph Clustering via Meta Weighting for Noisy Graphscited by 5
  26. 2024PreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep Intellectual Property Protectioncited by 3
  27. 2024UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Taskscited by 3
  28. 2024Revisiting Fake News Detection: Towards Temporality-aware Evaluation by Leveraging Engagement Earlinesscited by 3
  29. 2024HHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learningcited by 2
  30. 2025KGIF: Optimizing Relation-Aware Recommendations with Knowledge Graph Information Fusioncited by 2
  31. 2023Graph Neural Networks with a Distribution of Parametrized Graphscited by 1
  32. 2024Active Learning for Graphs with Noisy Structurescited by 1
  33. 2024Graph Contrastive Learning with Low-Rank Regularization and Low-Rank Attention for Noisy Node Classificationcited by 1
  34. 2025LiSA: Leveraging Link Recommender to Attack Graph Neural Networks via Subgraph Injectioncited by 1
  35. 2026Identifying and Correcting Label Noise for Robust GNNs via Influence Contradictioncited by 1
  36. 2024Energy Guided smoothness to improve Robustness in Graph Classificationcited by 0
  37. 2025Advanced Text Analytics -- Graph Neural Network for Fake News Detection in Social Mediacited by 0
  38. 2025Training Robust Graph Neural Networks by Modeling Noise Dependenciescited by 0

50 most cited of 63 All 63 (JSON)