ICML 2019oral16 citations

Distributed, Egocentric Representations of Graphs for Detecting Critical Structures

Ruo-Chun Tzeng, Shan-Hung Wu

Abstract

We study the problem of detecting critical structures using a graph embedding model. Existing graph embedding models lack the ability to precisely detect critical structures that are specific to a task at the global scale. In this paper, we propose a novel graph embedding model, called the Ego-CNNs, that employs the ego-convolutions convolutions at each layer and stacks up layers using an ego-centric way to detects precise critical structures efficiently. An Ego-CNN can be jointly trained with a task model and help explain/discover knowledge for the task. We conduct extensive experiments and the results show that Ego-CNNs (1) can lead to comparable task performance as the state-of-the-art graph embedding models, (2) works nicely with CNN visualization techniques to illustrate the detected structures, and (3) is efficient and can incorporate with scale-free priors, which commonly occurs in social network datasets, to further improve the training efficiency.

BibTeX
@InProceedings{pmlr-v97-tzeng19a,
  title = 	 {Distributed, Egocentric Representations of Graphs for Detecting Critical Structures},
  author =       {Tzeng, Ruo-Chun and Wu, Shan-Hung},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {6354--6362},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/tzeng19a/tzeng19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/tzeng19a.html},
  abstract = 	 {We study the problem of detecting critical structures using a graph embedding model. Existing graph embedding models lack the ability to precisely detect critical structures that are specific to a task at the global scale. In this paper, we propose a novel graph embedding model, called the Ego-CNNs, that employs the ego-convolutions convolutions at each layer and stacks up layers using an ego-centric way to detects precise critical structures efficiently. An Ego-CNN can be jointly trained with a task model and help explain/discover knowledge for the task. We conduct extensive experiments and the results show that Ego-CNNs (1) can lead to comparable task performance as the state-of-the-art graph embedding models, (2) works nicely with CNN visualization techniques to illustrate the detected structures, and (3) is efficient and can incorporate with scale-free priors, which commonly occurs in social network datasets, to further improve the training efficiency.}
}
Distributed, Egocentric Representations of Graphs for Detecting Critical Structures · ICML 2019