# Virtual Adversarial Training on Graph Convolutional Networks in Node Classification

arXiv: https://arxiv.org/abs/1902.11045 · HTML: https://mlsanity.com/paper/1902.11045/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2019.

## Built on by (most cited first, 11 of 11)

- [A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges](https://mlsanity.com/paper/2403.04468/) (2024)
- [Model Stealing Attacks Against Inductive Graph Neural Networks](https://mlsanity.com/paper/2112.08331/) (2021)
- [Are Defenses for Graph Neural Networks Robust?](https://mlsanity.com/paper/2301.13694/) (2023)
- [GrOVe: Ownership Verification of Graph Neural Networks using Embeddings](https://mlsanity.com/paper/2304.08566/) (2023)
- [Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective](https://mlsanity.com/paper/2105.08007/) (2021)
- [GraphAttacker: A General Multi-Task GraphAttack Framework](https://mlsanity.com/paper/2101.06855/) (2021)
- [EDoG: Adversarial Edge Detection For Graph Neural Networks](https://mlsanity.com/paper/2212.13607/) (2022)
- [On Generalization of Graph Autoencoders with Adversarial Training](https://mlsanity.com/paper/2107.02658/) (2021)
- [Graphfool: Targeted Label Adversarial Attack on Graph Embedding](https://mlsanity.com/paper/2102.12284/) (2021)
- [Understanding the Robustness of Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2406.13920/) (2024)
- [RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks](https://mlsanity.com/paper/2108.07481/) (2021)

## Abstract (arXiv)

The effectiveness of Graph Convolutional Networks (GCNs) has been demonstrated in a wide range of graph-based machine learning tasks. However, the update of parameters in GCNs is only from labeled nodes, lacking the utilization of unlabeled data. In this paper, we apply Virtual Adversarial Training (VAT), an adversarial regularization method based on both labeled and unlabeled data, on the supervised loss of GCN to enhance its generalization performance. By imposing virtually adversarial smoothness on the posterior distribution in semi-supervised learning, VAT yields improvement on the Symmetrical Laplacian Smoothness of GCNs. In addition, due to the difference of property in features, we perturb virtual adversarial perturbations on sparse and dense features, resulting in GCN Sparse VAT (GCNSVAT) and GCN Dense VAT (GCNDVAT) algorithms, respectively. Extensive experiments verify the effectiveness of our two methods across different training sizes. Our work paves the way towards better understanding the direction of improvement on GCNs in the future.