One2Multi Graph Autoencoder for Multi-view Graph Clustering

Fan, Shaohua; Wang, Xiao; Shi, Chuan; Lu, Emiao; Kang, Lin; Bai, Wei

doi:10.1145/3366423.3380079

Cited by 132 publications

(73 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Complex modern networks are represented by graphs. Graph clustering aims at partitioning graphs into several densely connected disjoint communities [19,20]. The deep community detection strategies can be divided into three big families: (i) AE-Based Community Detection (Auto-encoders are used), (ii) CNN/GNN-Based Community Detection (Convolutional Neural Networks (CNNs) and their variant Graph Neural Networks (GNNs) are used), and (iii) GAN-Based Community Detection (Generative Adversarial Networks (GANs) are used).…”

Section: Deep Community Detection Strategiesmentioning

confidence: 99%

A Survey on the Recent Advances of Deep Community Detection

2021

View full text Add to dashboard Cite

In the first days of social networking, the typical view of a community was a set of user profiles of the same interests and likes, and this community kept enlarging by searching, proposing, and adding new members with the same characteristics that were likely to interfere with the existing members. Today, things have changed dramatically. Social networking platforms are not restricted to forming similar user profiles: The vast amounts of data produced every day have given opportunities to predict and suggest relationships, behaviors, and everyday activities like shopping, food, traveling destinations, etc. Every day, vast data amounts are generated by the famous social networks such as Facebook, Twitter, Instagram, and so on. For example, Facebook alone generates 4 petabytes of data per day. The analysis of such data is of high importance to many aspects like recommendation systems, businesses, health organizations, etc. The community detection problem received considerable attention a long time ago. Communities are represented as clusters of an entire network. Most of the community detection techniques are based on graph structures. In this paper, we present the recent advances of deep learning techniques for community detection. We describe the most recent strategies presented in this field, and we provide some general discussion and some future trends.

show abstract

Section: Deep Community Detection Strategiesmentioning

confidence: 99%

A Survey on the Recent Advances of Deep Community Detection

2021

View full text Add to dashboard Cite

show abstract

“…MEGAN [50] was a multiplex GAN that designed a multilayer generator to model multilayer connectivity to generate fake samples and a node pair discriminator to enforce the generator to more accurately t the distribution of multilayer network connectivity. One2Multi [17] used the network with the most information as the input of encoder to learn the shared information of all the networks and then used a multidecoder to reconstruct the multiplex network from the shared information.…”

Section: Multiplex Network Embeddingmentioning

confidence: 99%

“…In addition to introducing the common vector, CrossMNA [16] also introduces a layer vector to extract the semantic meaning. One2Multi [17] uses one encoder to encode the most informative network from which we can extract the shared information and multiple decoders to reconstruct all layers learning the specific structure in each layer. DMNE [18] and MrMine [19] take advantage of the links between subgraphs or communities to learn the cross-network relationships.…”

Section: Introductionmentioning

confidence: 99%

Layer Information Similarity Concerned Network Embedding

Jiao

Wang

et al. 2021

Complexity

View full text Add to dashboard Cite

Great achievements have been made in network embedding based on single-layer networks. However, there are a variety of scenarios and systems that can be presented as multiplex networks, which can reveal more interesting patterns hidden in the data compared to single-layer networks. In the field of network embedding, in order to project the multiplex network into the latent space, it is necessary to consider richer structural information among network layers. However, current methods for multiplex network embedding mostly focus on the similarity of nodes in each layer of the network, while ignoring the similarity between different layers. In this paper, for multiplex network embedding, we propose a Layer Information Similarity Concerned Network Embedding (LISCNE) model considering the similarities between layers. Firstly, we introduce the common vector for each node shared by all layers and layer vectors for each layer where common vectors obtain the overall structure of the multiplex network and layer vectors learn semantics for each layer. We get the node embeddings in each layer by concatenating the common vectors and layer vectors with the consideration that the node embedding is related not only to the surrounding neighbors but also to the overall semantics. Furthermore, we define an index to formalize the similarity between different layers and the cross-network association. Constrained by layer similarity, the layer vectors with greater similarity are closer to each other and the aligned node embedding in these layers is also closer. To evaluate our proposed model, we conduct node classification and link prediction tasks to verify the effectiveness of our model, and the results show that LISCNE can achieve better or comparable performance compared to existing baseline methods.

show abstract

“…First, different dimensions of an given attributed multiplex network share the same node set and node attributes. Hence, different dimensions are typically similarities or may have some characteristics in common [28]. For instance, citation networks represent citations between papers.…”

Section: Introductionmentioning

confidence: 99%

“…Then, pre-trained node features are concatenated with the original node attributes to form new node attributes inputted into the two-layer GCNs [5] to learn each dimensional graph network respectively. At the same time, a regularized consistency constraint was then introduced to node embeddings from different dimension to learn similarities [28] between nodes and their counterparts in others dimension. And the learnable weight parameters of different GCNs for different dimensional graph networks were then constrained using a regularization term [26].…”

Section: Introductionmentioning

confidence: 99%

Node Classification in Attributed Multiplex Networks Using Random Walk and Graph Convolutional Networks

et al. 2022

View full text Add to dashboard Cite

Node classification, as a central task in the graph data analysis, has been studied extensively with network embedding technique for single-layer graph network. However, there are some obstacles when extending the single-layer network embedding technique to the attributed multiplex network. The classification of a given node in the attributed multiplex network must consider the network structure in different dimensions, as well as rich node attributes, and correlations among the different dimensions. Moreover, the distance node context information of a given node in each dimension will also affect the classification of the given node. In this study, a novel network embedding approach for the node classification of attributed multiplex networks using random walk and graph convolutional networks (AMRG) is proposed. A random walk network embedding technique was used to extract distant node information and the results are considered as pre-trained node features to be concatenated with the original node features inputted into the graph convolutional networks (GCNs) to learn node representations for each dimension. Besides, the consensus regularization is introduced to capture the similarities among different dimensions, and the learnable neural network parameters of GCNs for different dimensions are also constrained by the regularization mechanism to improve the correlations. As well as an attention mechanism is explored to infer the importance for a given node in different dimensions. Extensive experiments demonstrated that our proposed technique outperforms many competitive baselines on several real-world multiplex network datasets.

show abstract

One2Multi Graph Autoencoder for Multi-view Graph Clustering

Cited by 132 publications

References 15 publications

A Survey on the Recent Advances of Deep Community Detection

A Survey on the Recent Advances of Deep Community Detection

Layer Information Similarity Concerned Network Embedding

Node Classification in Attributed Multiplex Networks Using Random Walk and Graph Convolutional Networks

Contact Info

Product

Resources

About