A Unified Framework for Community Detection and Network Representation Learning

Tu, Cunchao; Zeng, Xiangkai; Wang, Hao; Zhang, Zhengyan; Liu, Zhiyuan; Sun, Maosong; Zhang, Bo; Lin, Leyu

doi:10.1109/tkde.2018.2852958

Cited by 99 publications

(49 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ou et al [24] employ graph embedding algorithm to preserve high-order proximities of large scale graphs and capture the asymmetric transitivity. Tu et al [25] consider user preference and social influence to improve the accuracy of social recommendation. Besides, network node incorporating the text content and label information can boost the quality of network embedding representation and improve the learning performance.…”

Section: A Network Embedding Methodsmentioning

confidence: 99%

Heterogeneous Information Network Embedding for Mention Recommendation

Feng

Jiang

2020

IEEE Access

View full text Add to dashboard Cite

Mention recommendation is the task of recommending the right candidate users in a message. Many works have been conducted on the problem of whom to mention. However, due to the sparsity and heterogeneous of mention data, none of them well solve the problem. The recent advances in network embedding representation learning provide an effective approach to model the sparsity and heterogeneous simultaneously in heterogeneous information network. To this end, we propose a novel Network Embedding Mention (NEM) recommendation model to recommend the right users in a message. NEM constructs a heterogeneous mention network based on different relationships among different entities. Then NEM learns a unified low dimensional embedding vector using random walk for users and messages by considering network structure and vertex content information. Finally, whom to mention is ranked by calculating the relevance scores from heterogeneous user and message embeddings. To evaluate the proposed method, we construct a large dataset and their corresponding social networks from a real-world social media platform. Through extensive experiments on real-world mention collection, we demonstrate that our proposed model outperforms the previous state-of-the-art methods in term of recommendation task.

show abstract

Section: A Network Embedding Methodsmentioning

confidence: 99%

Heterogeneous Information Network Embedding for Mention Recommendation

Feng

Jiang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…PNRL jointly optimizes two objectives for observed links and assumed hidden links. Tu et al [37] propose a Communityenhanced Network Representation Learning named CNRL. The algorithm shows its superiority on link prediction.…”

Section: Link Prediction 1)mentioning

confidence: 99%

MODEL: Motif-Based Deep Feature Learning for Link Prediction

Wang

Ren

et al. 2020

IEEE Trans. Comput. Soc. Syst.

View full text Add to dashboard Cite

Link prediction plays an important role in network analysis and applications. Recently, approaches for link prediction have evolved from traditional similarity-based algorithms into embedding-based algorithms. However, most existing approaches fail to exploit the fact that real-world networks are different from random networks. In particular, real-world networks are known to contain motifs, natural network building blocks reflecting the underlying network-generating processes. In this paper, we propose a novel embedding algorithm that incorporates network motifs to capture higher-order structures in the network. To evaluate its effectiveness for link prediction, experiments were conducted on three types of networks: social networks, biological networks, and academic networks. The results demonstrate that our algorithm outperforms both the traditional similarity-based algorithms (by 20%) and the stateof-the-art embedding-based algorithms (by 19%).

show abstract

“…NRL is also an important way to detect community. For example, Li et al [140] proposed a novel embedding based method for community detection leveraging both attributes and structure information of graphs, Tu et al [141] proposed unified FIGURE 9: Graph visualization of 20Newsgroups dataset. framework for community detection considering NRL and text modeling.…”

Section: E Other Applicationsmentioning

confidence: 99%

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Sun

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data. It has been successfully applied in many real-world tasks related to network science, such as social network data processing, biological information processing, and recommender systems. Deep Learning is a powerful tool to learn data features. However, it is non-trivial to generalize deep learning to graph-structured data since it is different from the regular data such as pictures having spatial information and sounds having temporal information. Recently, researchers proposed many deep learning-based methods in the area of NRL. In this survey, we investigate classical NRL from traditional feature learning method to the deep learning-based model, analyze relationships between them, and summarize the latest progress. Finally, we discuss open issues considering NRL and point out the future directions in this field.

show abstract

A Unified Framework for Community Detection and Network Representation Learning

Cited by 99 publications

References 58 publications

Heterogeneous Information Network Embedding for Mention Recommendation

Heterogeneous Information Network Embedding for Mention Recommendation

MODEL: Motif-Based Deep Feature Learning for Link Prediction

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Contact Info

Product

Resources

About