Learning Dynamic Context Graph Embedding

Chuanchang Chen, Yubo Tao, Hai Lin
Proceedings of The 12th Asian Conference on Machine Learning, PMLR 129:497-512, 2020.

Abstract

Graph embeddings represent nodes as low-dimensional vectors to preserve the proximity between nodes and communities of graphs for network analysis. The temporal edges (e.g., relationships, contacts, and emails) in dynamic graphs are important for graph evolution analysis, but few existing methods in graph embeddings can capture the dynamic information from temporal edges. In this study, we propose a dynamic graph embedding method to analyze the evolution patterns of dynamic graphs effectively. Our method uses diffuse context sampling to preserve the proximity between nodes, and applies dynamic context graph embeddings to train discrete-time graph embeddings in the same vector space without alignments to preserve the temporal continuity of stable nodes. We compare our method with several state-of-the-art methods for link prediction, and the experiments demonstrate that our method generally performs better at the task. Our method is further verified using a real-world dynamic graph by visualizing the evolution of its community structure at different timesteps.

Cite this Paper

BibTeX
@InProceedings{pmlr-v129-chen20c, title = {Learning Dynamic Context Graph Embedding}, author = {Chen, Chuanchang and Tao, Yubo and Lin, Hai}, booktitle = {Proceedings of The 12th Asian Conference on Machine Learning}, pages = {497--512}, year = {2020}, editor = {Pan, Sinno Jialin and Sugiyama, Masashi}, volume = {129}, series = {Proceedings of Machine Learning Research}, month = {18--20 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v129/chen20c/chen20c.pdf}, url = {https://proceedings.mlr.press/v129/chen20c.html}, abstract = {Graph embeddings represent nodes as low-dimensional vectors to preserve the proximity between nodes and communities of graphs for network analysis. The temporal edges (e.g., relationships, contacts, and emails) in dynamic graphs are important for graph evolution analysis, but few existing methods in graph embeddings can capture the dynamic information from temporal edges. In this study, we propose a dynamic graph embedding method to analyze the evolution patterns of dynamic graphs effectively. Our method uses diffuse context sampling to preserve the proximity between nodes, and applies dynamic context graph embeddings to train discrete-time graph embeddings in the same vector space without alignments to preserve the temporal continuity of stable nodes. We compare our method with several state-of-the-art methods for link prediction, and the experiments demonstrate that our method generally performs better at the task. Our method is further verified using a real-world dynamic graph by visualizing the evolution of its community structure at different timesteps.} }
Endnote
%0 Conference Paper %T Learning Dynamic Context Graph Embedding %A Chuanchang Chen %A Yubo Tao %A Hai Lin %B Proceedings of The 12th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Sinno Jialin Pan %E Masashi Sugiyama %F pmlr-v129-chen20c %I PMLR %P 497--512 %U https://proceedings.mlr.press/v129/chen20c.html %V 129 %X Graph embeddings represent nodes as low-dimensional vectors to preserve the proximity between nodes and communities of graphs for network analysis. The temporal edges (e.g., relationships, contacts, and emails) in dynamic graphs are important for graph evolution analysis, but few existing methods in graph embeddings can capture the dynamic information from temporal edges. In this study, we propose a dynamic graph embedding method to analyze the evolution patterns of dynamic graphs effectively. Our method uses diffuse context sampling to preserve the proximity between nodes, and applies dynamic context graph embeddings to train discrete-time graph embeddings in the same vector space without alignments to preserve the temporal continuity of stable nodes. We compare our method with several state-of-the-art methods for link prediction, and the experiments demonstrate that our method generally performs better at the task. Our method is further verified using a real-world dynamic graph by visualizing the evolution of its community structure at different timesteps.
APA
Chen, C., Tao, Y. & Lin, H.. (2020). Learning Dynamic Context Graph Embedding. Proceedings of The 12th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 129:497-512 Available from https://proceedings.mlr.press/v129/chen20c.html.

Related Material