Adversarially Regularized Graph Autoencoder for Graph Embedding

@inproceedings{Pan2018AdversariallyRG,
  title={Adversarially Regularized Graph Autoencoder for Graph Embedding},
  author={Shirui Pan and Ruiqi Hu and Guodong Long and Jing Jiang and Lina Yao and Chengqi Zhang},
  booktitle={IJCAI},
  year={2018}
}
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. [] Key Method 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.

Figures and Tables from this paper

Learning Graph Embedding With Adversarial Training Methods
TLDR
This article presents a novel adversarially regularized framework for graph embedding, employing the graph convolutional network as an encoder, that embeds the topological information and node content into a vector representation, from which a graph decoder is further built to reconstruct the input graph.
Adversarial Attention-Based Variational Graph Autoencoder
TLDR
The adversarial attention variational graph autoencoder (AAVGA) is a novel framework that incorporates attention networks into the encoder part and uses an adversarial mechanism in embedded training and proves that AAVGA performs competitively with state-of-the-art popular graph encoders on three citation datasets.
Graph Embedding Framework Based on Adversarial and Random Walk Regularization
TLDR
A novel graph embedding framework, Adversarial and Random Walk Regularized Graph Embedding (ARWR-GE), which jointly preserves structural and attribute information and is evaluated by using three real-world datasets on link prediction, graph clustering, and visualization tasks.
Feature-Dependent Graph Convolutional Autoencoders with Adversarial Training Methods
TLDR
A framework using autoencoder for graph embedding (GED) and its variational version (VEGD) and the Graph Convolutional Network (GCN) decoder of the proposed framework reconstructs both structural characteristics and node features, which naturally possesses the interaction between these two sources of information while learning the embedding.
Adversarially Regularized Graph Attention Networks for Inductive Learning on Partially Labeled Graphs
TLDR
This paper proposes a novel inductive embedding method for semi-supervised learning on graphs that generates node representations by learning a parametric function to aggregate information from the neighborhood using attention mechanism, and hence naturally generalizes to previously unseen nodes.
Adaptive Adversarial Attack on Graph Embedding via GAN
TLDR
An adaptive graph adversarial attack framework based on generative adversarial network (AGA-GAN), which generates the adversarial subgraph according to different attack strategies to rewire the corresponding parts in the original graph, and finally form the whole adversarial graph.
Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization
TLDR
A second view from the input network is created which captures the relation between nodes based on node content and enforce the latent representations from the two views to be consistent by incorporating a multiview adversarial regularization module.
Robust graph convolutional networks with directional graph adversarial training
TLDR
A graph-specific AT method, Directional Graph Adversarial Training (DGAT), which incorporates the graph structure into the adversarial process and automatically identifies the impact of perturbations from neighbor nodes, and introduces an adversarial regularizer to defend the worst-case perturbation.
Adversarial Graph Embedding for Ensemble Clustering
TLDR
A novel Adversarial Graph AutoEncoders (AGAE) model is proposed to incorporate ensemble clustering into a deep graph embedding process and an adversarial regularizer is developed to guide the network training with an adaptive partition-dependent prior.
Structural Adversarial Variational Auto-Encoder for Attributed Network Embedding
TLDR
Structural Adversarial Variational Graph Auto-Encoder (SAVGAE), a novel framework which encodes the network structure and node content into low-dimensional embeddings and learns the data distribution of each node representation while circumvents the side effect its sampling process causes on learning a robust embedding through adversarial training.
...
...

References

SHOWING 1-10 OF 57 REFERENCES
Adversarial Network Embedding
TLDR
An Adversarial Network Embedding (ANE) framework is proposed, which leverages the adversarial learning principle to regularize the representation learning and is competitive with or superior to state-of-the-art approaches on benchmark network embedding tasks.
MGAE: Marginalized Graph Autoencoder for Graph Clustering
TLDR
A marginalized graph convolutional network is proposed to corrupt network node content, allowing node content to interact with network features, and marginalizes the corrupted features in a graph autoencoder context to learn graph feature representations.
Deep Neural Networks for Learning Graph Representations
TLDR
A novel model for learning graph representations, which generates a low-dimensional vector representation for each vertex by capturing the graph structural information directly, and which outperforms other stat-of-the-art models in such tasks.
Variational Graph Auto-Encoders
TLDR
The variational graph auto-encoder (VGAE) is introduced, a framework for unsupervised learning on graph-structured data based on the variational auto- Encoder (VAE) that can naturally incorporate node features, which significantly improves predictive performance on a number of benchmark datasets.
A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications
TLDR
This survey conducts a comprehensive review of the literature in graph embedding and proposes two taxonomies ofGraph embedding which correspond to what challenges exist in differentgraph embedding problem settings and how the existing work addresses these challenges in their solutions.
Community Preserving Network Embedding
TLDR
A novel Modularized Nonnegative Matrix Factorization (M-NMF) model is proposed to incorporate the community structure into network embedding and jointly optimize NMF based representation learning model and modularity based community detection model in a unified framework, which enables the learned representations of nodes to preserve both of the microscopic and community structures.
Adversarial Autoencoders
TLDR
This paper shows how the adversarial autoencoder can be used in applications such as semi-supervised classification, disentangling style and content of images, unsupervised clustering, dimensionality reduction and data visualization, and performed experiments on MNIST, Street View House Numbers and Toronto Face datasets.
Learning Deep Representations for Graph Clustering
TLDR
This work proposes a simple method, which first learns a nonlinear embedding of the original graph by stacked autoencoder, and then runs $k$-means algorithm on the embedding to obtain the clustering result, which significantly outperforms conventional spectral clustering.
Structural Deep Network Embedding
TLDR
This paper proposes a Structural Deep Network Embedding method, namely SDNE, which first proposes a semi-supervised deep model, which has multiple layers of non-linear functions, thereby being able to capture the highly non- linear network structure and exploits the first-order and second-order proximity jointly to preserve the network structure.
Adversarial Feature Learning
TLDR
Bidirectional Generative Adversarial Networks are proposed as a means of learning the inverse mapping of GANs, and it is demonstrated that the resulting learned feature representation is useful for auxiliary supervised discrimination tasks, competitive with contemporary approaches to unsupervised and self-supervised feature learning.
...
...