Network Embedding via Community Based Variational Autoencoder

Wei, Shi; Huang, Ling; Wang, Chang‐Dong; Li, Juan-Hui; Tang, Yong; Fu, Chengjie

doi:10.1109/access.2019.2900662

Cited by 22 publications

(14 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another line of related work is network embedding and neural variational inference. Further researches [8,16,17,25,29] on network embedding for content-rich networks inspire us to learn the suitable neighbourhood contexts for users. Meanwhile, capturing the nonlinear correlation between text content and social network structure, and seamlessly fusing the two in the presentation space will provide more possibilities for detecting the latent topics of social media texts.…”

Section: Network Embedding and Neural Variational Inferencementioning

confidence: 99%

Fusing Parallel Social Contexts within Flexible-Order Proximity for Microblog Topic Detection

Liu

Wang

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Topic detection in social media is a challenging task due to largescale short, noisy and informal nature of messages. Most existing methods only consider textual content or simultaneously model the posts and the first-order structural characteristics of social networks. They ignore the impact of larger neighborhoods in microblog conversations on topics. Moreover, the simple combination of separated content and structure representations fails to capture their nonlinear correlation and different importance in topic inference. To this end, we propose a novel random walk based Parallel Social Contexts Fusion Topic Model (PCFTM) for weibo conversations. Firstly, a user-level conversation network with content information is built by the reposting and commenting relationships among users. Through random walks of different lengths on network, we obtain the user sequences containing the parallel content and structure contexts, which are used to acquire the flexible-order proximity of users. Then we propose a self-fusion network embedding to capture the nonlinear correlation between parallel social contexts. It is achieved by taking the content embedding sequence processed by CNN as the initial value of structure embedding sequence fed to Bi-LSTM. Meanwhile, a user-level self-attention is further used to mine the different importance of users to topics. Lastly, the user sequence embedding is incorporated into neural variational inference for detecting topics, which adaptively balances the intrinsic complementarity between content and structure, and fully uses both local and global social contexts in topic inference. Extensive experiments on three real-world weibo datasets demonstrate the effectiveness of our proposed model.

show abstract

Section: Network Embedding and Neural Variational Inferencementioning

confidence: 99%

Fusing Parallel Social Contexts within Flexible-Order Proximity for Microblog Topic Detection

Liu

Wang

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

show abstract

“…It jointly optimizes these two approximations to obtain the node representation using a highly nonlinear function. Some other methods are proposed using symmetry and asymmetry of networks to abstract global structures or community patterns [12]. GraRep [13] defines the k-order loss function on a graph that integrates the local structure information, which captures the global structure information of the graph.…”

Section: Related Workmentioning

confidence: 99%

“…MemeRep [14] uses a two-level learning strategy for local search, with the first level learning from neighboring nodes and the second level learning from the community. ComVAE [12] uses an auto-encoder to learn the local and community structure of the node jointly. However, these methods learn from the network structure without considering the attribute information.…”

Section: Related Workmentioning

confidence: 99%

Enhanced Network Representation Learning With Community Aware and Relational Attention

et al. 2020

View full text Add to dashboard Cite

Network representation learning is proposed to make it easier to perform complex inference processes on large-scale networks. It aims to represent each node in the network as a low-dimensional potential representation while preserving the structure and inherent features of the network. Most existing learning methods do not consider the comprehensive structure or the rich semantics of between nodes, which lead to incomplete embeddings. We attempt to find a way to learn network representation while keeping the network structure and relations between nodes to address this issue. In this paper, we propose a Community Aware and Relational Attention (CARA) method to enhance network representation learning. In CARA, community aware random walks capture both the community and local context from a global perspective to enhance the structure embedding. And we design a two-layer attention mechanism to model the semantic relationships between nodes, which can learn different text embedding for different neighbors. Then, these two embeddings are combined together to obtain the node representation. Experiments on four real-world networks show that CARA has better performance than other methods in link prediction and node classification.

show abstract

“…Applying random walk, DeepWalk [22] generates node sequences on graph firstly, and learns the node vectors with the help of the Skip-Gram [23] model. Both first-order and second-order proximities of nodes preserved, LINE [24] calculates node vectors with the two proximities respectively, and concatenates them directly.…”

Section: Introductionmentioning

confidence: 99%

The Deep Fusion of Topological Structure and Attribute Information for Link Prediction

et al. 2020

View full text Add to dashboard Cite

The link prediction can be used to seek missing or future links in the network, so it has become a hot research topic. The network generally contains two types of information: the topological structure of network formed by the connection between nodes, and the attribute information of nodes. However, the existing topology-based link prediction algorithms consider little attribute information. In this paper, a novel algorithm called Network Embedding with Attribute Deep Fusion for Link Prediction (NEADF-LP) is proposed. We get the embedded vectors with topological structure and attribute information by structure encoder and attribute encoder respectively, and fuse two vectors deeply. Compared with mainstream baselines on CiteSeer and Cora datasets, the results show that the deep fusion of topological structure and attribute information improve the accuracy of link prediction effectively. INDEX TERMS Complex network, deep fusion, link prediction, network embedding.

show abstract

Network Embedding via Community Based Variational Autoencoder

Cited by 22 publications

References 41 publications

Fusing Parallel Social Contexts within Flexible-Order Proximity for Microblog Topic Detection

Fusing Parallel Social Contexts within Flexible-Order Proximity for Microblog Topic Detection

Enhanced Network Representation Learning With Community Aware and Relational Attention

The Deep Fusion of Topological Structure and Attribute Information for Link Prediction

Contact Info

Product

Resources

About