Adversarially Regularized Graph Autoencoder for Graph Embedding

Pan, Shirui; Hu, Ruiqi; Long, Guodong; Jiang, Jing; Yao, Lina; Zhang, Chengqi

doi:10.24963/ijcai.2018/362

Cited by 621 publications

(324 citation statements)

References 2 publications

Supporting

Mentioning

280

Contrasting

Unclassified

Order By: Relevance

“…In [27] and [12], uniform random walks and BFS/DFS-like random walks are used, respectively. Another type of graph embedding methods [18,25,36,13] is based on adjacency matrices of graphs. In [36], the first-order and second-order proximity is used to represent the network structure.…”

Section: Static Graph Embeddingsmentioning

confidence: 99%

“…Graph embedding methods are helpful to reduce the high dimensionality of graph data by learning low-dimensional features as latent representations. Many embedding algorithms [31,12,27,2,18,25,8,13,1,4,8,2,37,35,24,3] have been proposed to capture different characteristics of a network and they provide effective ways to extract low-dimensional latent representations of graphs.…”

Section: Introductionmentioning

confidence: 99%

“…The problem of this joint optimization function is a non-convex and non-linear optimization problem with a large number of variables. Recently, different types of deep autoencoders have been proposed to solve complex nonlinear functions [25,13,36]. Among the autoencoders, variational graph auto-encoder (VGAE) [18] is an effective static embedding method which is a deep generative model by variational inference.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic Joint Variational Graph Autoencoders

Mahdavi

Khoshraftar

2020

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

Learning network representations is a fundamental task for many graph applications such as link prediction, node classification, graph clustering, and graph visualization. Many real-world networks are interpreted as dynamic networks and evolve over time. Most existing graph embedding algorithms were developed for static graphs mainly and cannot capture the evolution of a large dynamic network. In this paper, we propose Dynamic joint Variational Graph Autoencoders (Dyn-VGAE) that can learn both local structures and temporal evolutionary patterns in a dynamic network. Dyn-VGAE provides a joint learning framework for computing temporal representations of all graph snapshots simultaneously. Each auto-encoder embeds a graph snapshot based on its local structure and can also learn temporal dependencies by collaborating with other autoencoders. We conduct experimental studies on dynamic real-world graph datasets and the results demonstrate the effectiveness of the proposed method.

show abstract

Section: Static Graph Embeddingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Joint Variational Graph Autoencoders

Mahdavi

Khoshraftar

2020

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

show abstract

“…Simonovsky and Komodakis in [12] used a generative model to produces a probabilistic graph from a single opaque vector without specifying the number of nodes or the structure explicitly. Pan and et al in [13] proposed an adversarial training scheme to regularize and enforce the latent code to match a prior distribution with a graph convolutional Autoencoder. Makhzani in [14] showed an adversarial Autoencoder to learn the latent embedding by merging the adversarial mechanism into Autoencoder for general data but Dai and et al [15] applied the adversarial procedure for the graph embedding.…”

Section: Related Workmentioning

confidence: 99%

Graph-Based Method for Anomaly Detection in Functional Brain Network using Variational Autoencoder

Mirakhorli

2019

Preprint

View full text Add to dashboard Cite

Functional neuroimaging techniques using resting-state functional MRI (rs-fMRI) have accelerated progress in brain disorders and dysfunction studies. Since, there are the slight differences between healthy and disorder brains, investigation in the complex topology of human brain functional networks is difficult and complicated task with the growth of evaluation criteria. Recently, graph theory and deep learning applications have spread widely to understanding human cognitive functions that are linked to gene expression and related distributed spatial patterns. Irregular graph analysis has been widely applied in many brain recognition domains, these applications might involve both node-centric and graph-centric tasks. In this paper, we discuss about individual Variational Autoencoder and Graph Convolutional Network (GCN) for the region of interest identification areas of brain which do not have normal connection when apply certain tasks. Here, we identified a framework of Graph Auto-Encoder (GAE) with hyper sphere distributer for functional data analysis in brain imaging studies that is underlying non-Euclidean structure, in learning of strong rigid graphs among large scale data. In addition, we distinguish the possible mode correlations in abnormal brain connections.

show abstract

“…Neural networks on graph, such as GCN [35], also obtain the embeddings for each node. Some studies explore the structural regularity regarding the regular equivalence [36], the embedding distribution [37] and the computational challenges [38], while others attempt to incorporate the heterogeneous information [39], [40]. Recently, a few works investigate the problem of dynamic network embedding.…”

Section: B Network Embeddingmentioning

confidence: 99%

DNA: Dynamic Social Network Alignment

Zhang

et al. 2019

2019 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Social network alignment, aligning different social networks on their common users, is receiving dramatic attention from both academic and industry. All existing studies consider the social network to be static and neglect its inherent dynamics. In fact, the dynamics of social networks contain the discriminative pattern of an individual, which can be leveraged to facilitate social network alignment. Hence, we for the first time propose to study the problem of aligning dynamic social networks. Towards this end, we propose a novel Dynamic social Network Alignment (DNA) framework, a unified optimization approach over deep neural architectures, to unfold the fruitful dynamics to perform alignment. However, it faces tremendous challenges in both modeling and optimization: (1) To model the intranetwork dynamics, we explore the local dynamics of the latent pattern in friending evolvement and the global consistency of the representation similarity with neighbors. We design a novel deep neural architecture to obtain the dual embedding capturing local dynamics and global consistency for each user.(2) To model the inter-network alignment, we exploit the underlying identity of an individual from the dual embedding in each dynamic social network. We design a unified optimization approach interplaying proposed deep neural architectures to construct a common subspace of identity embeddings. (3) To address this optimization problem, we design an effective alternating algorithm with solid theoretical guarantees. We conduct extensive experiments on realworld datasets and show that the proposed DNA framework substantially outperforms the state-of-the-art methods.

show abstract

Adversarially Regularized Graph Autoencoder for Graph Embedding

Cited by 621 publications

References 2 publications

Dynamic Joint Variational Graph Autoencoders

Dynamic Joint Variational Graph Autoencoders

Graph-Based Method for Anomaly Detection in Functional Brain Network using Variational Autoencoder

DNA: Dynamic Social Network Alignment

Contact Info

Product

Resources

About