MGAE: Marginalized Graph Autoencoder for Graph Clustering

By C. Wang, Shirui Pan, Guodong Long, Xingquan Zhu, Jing Jiang. 2017

521 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Shirui Pan
2. Philip S. Yu
3. Zhiyuan Liu
4. Guodong Long
5. Chengqi Zhang
6. Jing Jiang
7. Maosong Sun
8. Jie Zhou

In Molecular Biology

1. Shirui Pan
2. Chengqi Zhang
3. Guodong Long
4. Jing Jiang
5. Ruiqi Hu
6. Philip S. Yu
7. Cécile Paris
8. Yaochen Xie

In Statistical and Nonlinear Physics

1. Shirui Pan
2. Chengqi Zhang
3. Guodong Long
4. Jing Jiang
5. Ruiqi Hu
6. Philip S. Yu
7. Cheng Yang
8. Zhiyuan Liu

Citations in the corpus

• Adversarially Regularized Graph Autoencoder (2018, background): “SDNE [Wang et al. , 2016] and DNGR [Cao et al. , 2016] employ deep autoencoders to preserve the graph proximities and model positive pointwise mutual information (PPMI).”
• A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning (2021, methodology): “MAGE [24] first employs a convolutional network to integrate content and structure information, and then iteratively adds random noises to content information in the auto-encoder process.”
• Multi-view Contrastive Graph Clustering (2021, unknown): “It reports better performance than variational GAE (VGAE) [Kipf and Welling, 2016], marginalized GAE (MGAE) [Wang et al., 2017], adversarially regularized GAE (ARGA) and VGAE (ARVGA) [Pan et al., 2018], and GALA [Park et al., 2019].”
• Graph Neural Networks: A Review of Methods and Applications (2018, methodology): “MGAE (Wang et al., 2017) utilizes marginalized denoising auto-encoder to get robust node representation.”
• Attributed Graph Clustering: A Deep Attentional Embedding Approach (2019, methodology): “Many embedding learning based approaches apply an existing clustering algorithm on the learned embedding [ Wang et al. , 2017b ] .”
• A Comprehensive Survey on Community Detection With Deep Learning (2021, background): “Marginalized graph autoencoder (MGAE) [124] denoises both graph attributes and structures to improve community detection through a marginalization process.”
• Graph Self-Supervised Learning: A Survey (2021, background): “MGAE [44] FG Node JL Attributed Feature Noising Node Feature”
• Network Representation Learning: A Survey (2017, background): “Only very recently, a few studies have started to design task-specific NRL algorithms for link prediction [35], community detection [98], [99], [100], [101], class imbalance learning [102], active learning [103], and information retrieval [104].”
• Self-Supervised Learning of Graph Neural Networks: A Unified Review (2021, methodology): “For example, GAE [39] performs reconstruction on the adjacency matrix, and MGAE [50] performs reconstruction on randomly corrupted node attributes.”
• Attributed Graph Clustering via Adaptive Graph Convolution (2019, methodology): “In particular, GCN based methods such as GAE [Kipf and Welling, 2016], MGAE [Wang et al., 2017], ARGE [Pan et al.”
• Learning Graph Embedding With Adversarial Training Methods (2019, methodology): “The MGAE algorithm utilizes a marginalized single-layer autoencoder to learn representation for graph clustering [2].”
• Contrastive Multi-View Representation Learning on Graphs (2020, methodology): “, 2019) including: variational GAE (VGAE) (Kipf & Welling, 2016), marginalized GAE (MGAE) (Wang et al., 2017), adversarially regularized GAE (ARGA) and VGAE (ARVGA) (Pan et al.”