Adversarially Regularized Graph Autoencoder for Graph Embedding
Open accessAbstract
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
One simple way to learn graph embeddings unsupervisedly is to adopt an autoencoder framework where the encoder employs graph convolutional layers to embed the graph into a latent representation and a decoder reconstructs the graph structure.
“One simple way is to adopt an autoencoder framework where the encoder employs graph convolutional layers to embed the graph into the latent representation upon which a decoder is used to reconstruct the graph structure [61], [62].”
From A Comprehensive Survey on Graph Neural Networks (2021) · cites this paper as [62]
ARVGA employs the training scheme of a GAN to enforce the empirical distribution q(Z|X,A) to approximate the prior distribution p(Z).
“To further enforce the empirical distribution q ( Z | X , A ) approximate the prior distribution p ( Z ) , Adversarially Regularized Variational Graph Autoencoder (ARVGA) [62], [109] employs the training scheme of a generative adversarial networks (GAN) [110].”
From A Comprehensive Survey on Graph Neural Networks (2021) · cites this paper as [62]
ARVGA employs the training scheme of a GAN to enforce the empirical distribution q(Z|X,A) to approximate the prior distribution p(Z).
“To further enforce the empirical distribution q ( Z | X , A ) approximate the prior distribution p ( Z ) , Adversarially Regularized Variational Graph Autoencoder (ARVGA) [62], [109] employs the training scheme of a generative adversarial networks (GAN) [110].”
From A Comprehensive Survey on Graph Neural Networks (2021) · cites this paper as [109]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,100 · see citing works
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · see citing works
DeepWalk: online learning of social representations
Perozzi, B., Al-Rfou, R., & Skiena, S. (2014) · Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2623330.2623732 · Cited by 10,123 · see citing works
LINE: Large-scale Information Network Embedding
Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., & Mei, Q. (2015) · Proceedings of the 24th International Conference on World Wide Web · doi:10.1145/2736277.2741093 · Cited by 5,416 · see citing works
Structural Deep Network Embedding
Wang, D., Cui, P., & Zhu, W. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939753 · Cited by 2,845 · see citing works
Accelerating t-SNE using tree-based algorithms
van der Maaten, L. (2014) · Journal of machine learning research · doi:10.5555/2627435.2697068 · Cited by 2,207 · see citing works
A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications
Cai, H., Zheng, V. W., & Chang, K. C.-C. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2807452 · Cited by 2,034 · see citing works
Adversarial Feature LearningPreprint
Donahue, J., Krähenbühl, P., & Darrell, T. (2016) · International Conference on Learning Representations · doi:10.48550/arxiv.1605.09782 · Cited by 1,982 · see citing works
Identifying Resilient Communities in Road Networks: A Path-Based Embedding Approach
Wagner, C., Dodge, S., & Alizadeh, D. (2025) · Leibniz international proceedings in informatics · doi:10.4230/lipics.giscience.2025.9 · Cited by 1,599 · see citing works
Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., & Frey, B. (2015) · arXiv · doi:10.48550/arxiv.1511.05644 · Cited by 1,579 · see citing works
Asymmetric Transitivity Preserving Graph Embedding
Ou, M., Cui, P., Pei, J., Zhang, Z., & Zhu, W. (2016) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2939672.2939751 · Cited by 1,298 · see citing works
Cui, P., Wang, X., Pei, J., & Zhu, W. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2018.2849727 · Cited by 1,274 · see citing works
Deep Neural Networks for Learning Graph Representations
Cao, S., Lu, W., & Xu, Q. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10179 · Cited by 1,070 · see citing works
Network representation learning with rich text information
Yang, C. H., Liu, Z., Zhao, D., Sun, M., & Chang, E. Y. (2015) · Cited by 977 · see citing works
Community Preserving Network Embedding
Wang, X., Cui, P., Wang, J., Pei, J., Zhu, W., & Yang, S. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10488 · Cited by 935 · see citing works
Energy-based Generative Adversarial Network
Zhao, J., Mathieu, M., & LeCun, Y. (2016) · arXiv · doi:10.48550/arxiv.1609.03126 · Cited by 912 · cited 2× · see citing works
“, 2016], EBGAN [Zhao et al., 2016] and ALI [Dumoulin et al.”
BackgroundRobust Multi-View Spectral Clustering via Low-Rank and Sparse Decomposition
Xia, R., Pan, Y., Du, L., & Yin, J. P. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8950 · Cited by 760 · see citing works
Network Representation Learning: A Survey
Zhang, D., Yin, J., Zhu, X., & Zhang, C. (2020) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2018.2850013 · Cited by 714 · see citing works
Self-citationLearning Deep Representations for Graph Clustering
Tian, F., Gao, B., Cui, Q., Chen, E., & Liu, T. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8916 · Cited by 680 · see citing works
Relational Topic Models for Document Networks
Chang, J., & Blei, D. M. (2009) · Cited by 477 · see citing works
Tri-party deep network representation
Pan, S., Wu, J. X., Xingquan Zhu, A., Zhang, C., & Wang, Y. (2016) · Griffith Research Online · Cited by 376 · see citing works
Self-citationLeveraging social media networks for classification
Tang, L., & Liu, H. (2011) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-010-0210-x · Cited by 360 · see citing works
Dai, Q., Li, Q., Tang, J., & Wang, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11865 · Cited by 214 · see citing works
A Comprehensive Survey of Graph Embedding: Problems, Techniques and ApplicationsPreprint
Cai, H., Zheng, V. W., & Chang, K. C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.07604 · Cited by 152 · see citing works
User Profile Preserving Social Network Embedding
Zhang, D., Yin, J., Xingquan Zhu, A., & Zhang, C. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/472 · Cited by 86 · see citing works
Self-citationAdversarial Network EmbeddingPreprint
Dai, Q., Li, Q., Tang, J. G., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.07838 · Cited by 68 · see citing works
Predictive Network Representation Learning for Link Prediction
Wang, Z., Chen, C., & Li, W. (2017) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3077136.3080692 · Cited by 63 · see citing works
A Survey on Network EmbeddingPreprint
Cui, P., Wang, X., Pei, J., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.08752 · Cited by 47 · see citing works
Network Representation Learning: A SurveyPreprint
Zhang, D., Yin, J., Zhu, X., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.05852 · Cited by 44 · see citing works
Joint structure feature exploration and regularization for multi-task graph classification
Pan, S., Wu, J. X., Zhuy, X., et al. (2016) · Proceedings - International Conference on Data Engineering · doi:10.1109/icde.2016.7498381 · Cited by 10 · see citing works
Self-citationChen, T., Wang, Z., Li, L., Li, D., Li, Z., Chang, X., Bian, P., Liang, G., Wang, Q., & Xie, T. (2025) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.ecoop.2025.6
Flagged first, then by citations
Research works printed but not linked: 7
- Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial nets. In NIPS, pages 2672-2680, 2014.
- Grover and Leskovec, 2016] Aditya Grover and Jure Leskovec. node2vec: Scalable feature learning for networks. In SIGKDD, pages 855-864. ACM, 2016.
- Thomas N Kipf and Max Welling. Variational graph auto-encoders. NIPS, 2016.
- Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In ICLR, pages 1-14, 2017.
- Qiu et al., 2017] Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, and Jie Tang. Network embedding as matrix factorization: Unifying deepwalk, line, pte, and node2vec. arXiv preprint arXiv:1710.02971, 2017. · arXiv
- Wang et al., 2017a] Chun Wang, Shirui Pan, Guodong Long, Xingquan Zhu, and Jing Jiang. Mgae: Marginalized graph autoencoder for graph clustering. In CIKM, pages 889-898. ACM, 2017.
- Wang et al., 2017b] Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, and Shiqiang Yang. Community preserv- ing network embedding. In AAAI, pages 203-209, 2017.
Cited by
Sorted by citations
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · see citing works
Self-citationGraph neural networks: A review of methods and applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020) · AI Open · doi:10.1016/j.aiopen.2021.01.001 · Cited by 6,880 · see citing works
Binarized attributed network embedding
Yang, H., Pan, S., Zhang, P., Chen, L., Lian, D., & Zhang, C. (2018) · 2018 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm.2018.8626170 · Cited by 102 · see citing works
Self-citationAdversarial Label-Flipping Attack and Defense for Graph Neural Networks
Zhang, M., Hu, L., Shi, C., & Wang, X. (2020) · 2020 IEEE International Conference on Data Mining (ICDM) · doi:10.1109/icdm50108.2020.00088 · Cited by 74 · see citing works
Yao, H., Guan, J., & Liu, T. (2020) · Journal of Bioinformatics and Computational Biology · doi:10.1142/s0219720020400107 · Cited by 23 · see citing works
- Authors
- Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., & Zhang, C.
- Affiliations
- University of Technology Sydney (AU)
- UNSW Sydney (AU)
- Venue
- Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
- Published
- 2018-07
- Pages
- 2609-2615
- OpenAlex
- W2808409763
- Cited by
- 929
- References
- 31
- Citations by year
- 2026: 56 · 2025: 123 · 2024: 151 · 2023: 157 · 2022: 148 · 2021: 152 · 2020: 97 · 2019: 39 · 2018: 6
- FWCI
- 30.02
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- UTS ePRESS (University of Technology Sydney) (submittedVersion)
- Griffith Research Online (submittedVersion)
- Funders
- Nvidia
- Australian Research Council (LP160100630, LP150100671)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Graph Theory and Algorithms
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Network Analysis Techniques
- Keywords
- graph embedding, graph autoencoder, adversarial training, variational graph autoencoder, adversarial regularization, link prediction, graph clustering, network visualization, latent representation learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
