Signed Network Embedding in Social Media

By Suhang Wang, Jiliang Tang, Charu C. Aggarwal, Yi Chang, Huan Liu. 2017

258 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chengqi Zhang
2. Xing Xie
3. Hongwei Wang
4. Jiliang Tang
5. Fuzheng Zhang
6. Minyi Guo
7. Miao Zhao
8. Peng Cui

In Statistical and Nonlinear Physics

1. Chengqi Zhang
2. Huan Liu
3. Peng Cui
4. Xiao Wang
5. Wenwu Zhu
6. Xingquan Zhu
7. Kai Shu
8. Jie Yin

Citations in the corpus

• SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction (2017, background): “ address unsigned and homogeneous networks. Additionally, several studies focus on representation learning in the scenario of heterogeneous network [3, 32], attributed network [10], or signed network [29, 33]. However, these methods are specialized in only one particular type of networks, which is n”
• Fake News Detection on Social Media: A Data Mining Perspective (2017, background): “w other networks can be constructed in terms of dierent aspects of relationships among relevant users and posts; and (ii) other advanced methods of network representations, such as network embedding [78;86]. Model-oriented: Model-oriented fake news research opens the door to building more eective an”
• DEBAGREEMENT: A comment-reply dataset for (dis)agreement detection in online debates (2021, methodology): “Modeling online discussion forums as graphs of interactions between users enables researchers to: i) translate the (dis)agreement detection task into a sign link prediction one [45], ii) use recent advances in GRL methods [20], and iii) leverage existing signed graph embedding methods [41, 15, 30] t”
• Deep Network Embedding for Graph Representation Learning in Signed Networks (2019, methodology): “following [29], [30], and [39], we adopted the “area under the ROC curve” (AUC) metric to evaluate the link sign prediction performance, which is insensitive to the imbal-”
• Network Representation Learning: A Survey (2017, background): “Some studies [122], [123], [124] tackle signed network representation learning through directly modeling the polar of links.”
• Signed Graph Convolutional Networks (2018, methodology): “• SiNE [19]: This method is a deep learning framework that utilized extended structural balance theory.”
• A Survey on Network Embedding (2017, methodology): “Network Communities Wang et al. (Wang et al. 2017b) propose a modularized nonnegative matrix factorization (M-NMF) model for network embedding, which aims to preserve both the microscopic structure, i.e., the first-order and second-order proximities of nodes, and the mesoscopic community structure (G”
• GraphGAN: Graph Representation Learning with Generative Adversarial Nets (2017, methodology): “In addition, several prior works also try to preserve spe-cific properties during the learning process, such as global structures (Wang, Cui, and Zhu 2016), community structures (Wang et al. 2017c), group information (Chen, Zhang, and Huang 2016), and asymmetric transitivity (Ou et al. 2016).”