mlsanityData to 7 Oct 2026

Batch Virtual Adversarial Training for Graph Convolutional Networks

arXiv 1902.09192 ↗First posted 25 Feb 2019cs.LG cs.AI stat.MLcited by 33

Not on the map. Why?

Abstract (arXiv)

We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the shortcoming of GCNs that do not consider the smoothness of the model's output distribution against local perturbations around the input. We propose two algorithms, sample-based BVAT and optimization-based BVAT, which are suitable to promote the smoothness of the model for graph-structured data by either finding virtual adversarial perturbations for a subset of nodes far from each other or generating virtual adversarial perturbations for all nodes with an optimization process. Extensive experiments on three citation network datasets Cora, Citeseer and Pubmed and a knowledge graph dataset Nell validate the effectiveness of the proposed method, which establishes state-of-the-art results in the semi-supervised node classification tasks.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 10; 2023: 4; 2024: 4; 2025: 1; 2026: 1.

33 papers.

Sort:

  1. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 132
  2. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  3. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  4. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  5. 2021Local Augmentation for Graph Neural Networkscited by 52
  6. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  7. 2021AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filtercited by 43
  8. 2023Are Defenses for Graph Neural Networks Robust?cited by 38
  9. 2021Tree Decomposed Graph Neural Networkcited by 35
  10. 2022Metropolis-Hastings Data Augmentation for Graph Neural Networkscited by 30
  11. 2023Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directionscited by 28
  12. 2021Curvature Graph Neural Networkcited by 24
21 more
  1. 2022Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervisioncited by 16
  2. 2021CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networkscited by 15
  3. 2021Adaptive Kernel Graph Neural Networkcited by 15
  4. 2022NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphscited by 14
  5. 2022Spectral Adversarial Training for Robust Graph Neural Networkcited by 12
  6. 2021SCR: Training Graph Neural Networks with Consistency Regularizationcited by 10
  7. 2021Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspectivecited by 9
  8. 2023Robust Graph Neural Networks via Unbiased Aggregationcited by 8
  9. 2021Calibrating and Improving Graph Contrastive Learningcited by 6
  10. 2022EDoG: Adversarial Edge Detection For Graph Neural Networkscited by 4
  11. 2021On Generalization of Graph Autoencoders with Adversarial Trainingcited by 3
  12. 2021Network representation learning: A macro and micro viewcited by 3
  13. 2024Uncertainty Quantification on Graph Learning: A Surveycited by 3
  14. 2022LEReg: Empower Graph Neural Networks with Local Energy Regularizationcited by 2
  15. 2022Context-based Virtual Adversarial Training for Text Classification with Noisy Labelscited by 1
  16. 2023Distributional Signals for Node Classification in Graph Neural Networkscited by 1
  17. 2024Understanding the Robustness of Graph Neural Networks against Adversarial Attackscited by 1
  18. 2024Adversarial Training for Graph Neural Networks via Graph Subspace Energy Optimizationcited by 1
  19. 2025Unifying Adversarial Perturbation for Graph Neural Networkscited by 1
  20. 2021Customizing Graph Neural Networks using Path Reweightingcited by 0
  21. 2026Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluationcited by 0