On Generalization of Graph Autoencoders with Adversarial Training
Not on the map. Why?
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 6 Jul 2021.
Builds on
27 of 33 references.
References · 27
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
- 2014DeepWalk: Online Learning of Social Representationscited by 1,543
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2016Variational Graph Auto-Encoderscited by 1,373
- 2018Robustness May Be at Odds with Accuracycited by 873
- 2015LINE: Large-scale Information Network Embeddingcited by 582
- 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
- 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
15 more
- 2018Disentangling Adversarial Robustness and Generalizationcited by 171
- 2019Graph Adversarial Training: Dynamically Regularizing Based on Graph Structurecited by 93
- 2018Adversarially Regularized Graph Autoencoder for Graph Embeddingcited by 84
- 2019Graph-Revised Convolutional Networkcited by 58
- 2019Batch Virtual Adversarial Training for Graph Convolutional Networkscited by 33
- 2019Gravity-Inspired Graph Autoencoders for Directed Link Predictioncited by 28
- 2020ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detectioncited by 27
- 2019Adversarial Training Methods for Network Embeddingcited by 26
- 2020ResGCN: Attention-based Deep Residual Modeling for Anomaly Detection on Attributed Networkscited by 24
- 2020Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classificationcited by 18
- 2020Simple and Effective Graph Autoencoders with One-Hop Linear Modelscited by 17
- 2019GraphDefense: Towards Robust Graph Convolutional Networkscited by 16
- 2019Effective Decoding in Graph Auto-Encoder using Triadic Closurecited by 13
- 2019Virtual Adversarial Training on Graph Convolutional Networks in Node Classificationcited by 11
- 2019Can Adversarial Network Attack be Defended?cited by 10
Built on by
Citing papers per year: 2022: 2; 2023: 0; 2024: 0; 2025: 1.
3 papers.