Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization

Qiuhao Lu, Nisansa de Silva, Dejing Dou, Thien Huu Nguyen, Prithviraj Sen, Berthold Reinwald, Yunyao Li


Abstract
Network representation learning (NRL) is crucial in the area of graph learning. Recently, graph autoencoders and its variants have gained much attention and popularity among various types of node embedding approaches. Most existing graph autoencoder-based methods aim to minimize the reconstruction errors of the input network while not explicitly considering the semantic relatedness between nodes. In this paper, we propose a novel network embedding method which models the consistency across different views of networks. More specifically, we create a second view from the input network which captures the relation between nodes based on node content and enforce the latent representations from the two views to be consistent by incorporating a multiview adversarial regularization module. The experimental studies on benchmark datasets prove the effectiveness of this method, and demonstrate that our method compares favorably with the state-of-the-art algorithms on challenging tasks such as link prediction and node clustering. We also evaluate our method on a real-world application, i.e., 30-day unplanned ICU readmission prediction, and achieve promising results compared with several baseline methods.
Anthology ID:
2020.coling-main.47
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
545–555
Language:
URL:
https://aclanthology.org/2020.coling-main.47
DOI:
10.18653/v1/2020.coling-main.47
Bibkey:
Cite (ACL):
Qiuhao Lu, Nisansa de Silva, Dejing Dou, Thien Huu Nguyen, Prithviraj Sen, Berthold Reinwald, and Yunyao Li. 2020. Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization. In Proceedings of the 28th International Conference on Computational Linguistics, pages 545–555, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization (Lu et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2020.coling-main.47.pdf
Code
 qiuhaolu/mrgae
Data
Pubmed