# On Generalization of Graph Autoencoders with Adversarial Training

arXiv: https://arxiv.org/abs/2107.02658 · HTML: https://mlsanity.com/paper/2107.02658/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 33 references that are in the map.
- First posted on arXiv 6 Jul 2021.

## Builds on (most cited first, 27 of 27)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [LINE: Large-scale Information Network Embedding](https://mlsanity.com/paper/1503.03578/) (2015)
- [Do Adversarially Robust ImageNet Models Transfer Better?](https://mlsanity.com/paper/2007.08489/) (2020)
- [Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective](https://mlsanity.com/paper/1906.04214/) (2019)
- [Disentangling Adversarial Robustness and Generalization](https://mlsanity.com/paper/1812.00740/) (2018)
- [Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure](https://mlsanity.com/paper/1902.08226/) (2019)
- [Adversarially Regularized Graph Autoencoder for Graph Embedding](https://mlsanity.com/paper/1802.04407/) (2018)
- [Graph-Revised Convolutional Network](https://mlsanity.com/paper/1911.07123/) (2019)
- [Batch Virtual Adversarial Training for Graph Convolutional Networks](https://mlsanity.com/paper/1902.09192/) (2019)
- [Gravity-Inspired Graph Autoencoders for Directed Link Prediction](https://mlsanity.com/paper/1905.09570/) (2019)
- [ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detection](https://mlsanity.com/paper/2003.05669/) (2020)
- [Adversarial Training Methods for Network Embedding](https://mlsanity.com/paper/1908.11514/) (2019)
- [ResGCN: Attention-based Deep Residual Modeling for Anomaly Detection on Attributed Networks](https://mlsanity.com/paper/2009.14738/) (2020)
- [Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification](https://mlsanity.com/paper/2007.05869/) (2020)
- [GraphDefense: Towards Robust Graph Convolutional Networks](https://mlsanity.com/paper/1911.04429/) (2019)
- [Simple and Effective Graph Autoencoders with One-Hop Linear Models](https://mlsanity.com/paper/2001.07614/) (2020)
- [Effective Decoding in Graph Auto-Encoder using Triadic Closure](https://mlsanity.com/paper/1911.11322/) (2019)
- [Virtual Adversarial Training on Graph Convolutional Networks in Node Classification](https://mlsanity.com/paper/1902.11045/) (2019)
- [Can Adversarial Network Attack be Defended?](https://mlsanity.com/paper/1903.05994/) (2019)

## Built on by (most cited first, 3 of 3)

- [Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction](https://mlsanity.com/paper/2202.00961/) (2022)
- [Enhancing Robust Fairness via Confusional Spectral Regularization](https://mlsanity.com/paper/2501.13273/) (2025)
- [New Frontiers in Graph Autoencoders: Joint Community Detection and Link Prediction](https://mlsanity.com/paper/2211.08972/) (2022)

## Abstract (arXiv)

Adversarial training is an approach for increasing model's resilience against adversarial perturbations. Such approaches have been demonstrated to result in models with feature representations that generalize better. However, limited works have been done on adversarial training of models on graph data. In this paper, we raise such a question { does adversarial training improve the generalization of graph representations. We formulate L2 and L1 versions of adversarial training in two powerful node embedding methods: graph autoencoder (GAE) and variational graph autoencoder (VGAE). We conduct extensive experiments on three main applications, i.e. link prediction, node clustering, graph anomaly detection of GAE and VGAE, and demonstrate that both L2 and L1 adversarial training boost the generalization of GAE and VGAE.