Graph Capsule Convolutional Neural Networks

@article{Verma2018GraphCC,
  title={Graph Capsule Convolutional Neural Networks},
  author={Saurabh Verma and Zhi-Li Zhang},
  journal={CoRR},
  year={2018},
  volume={abs/1805.08090}
}
Graph Convolutional Neural Networks (GCNNs) are the most recent exciting advancement in deep learning field and their applications are quickly spreading in multi-cross-domains including bioinformatics, chemoinformatics, social networks, natural language processing and computer vision. In this paper, we expose and tackle some of the basic weaknesses of a GCNN model with a capsule idea presented in (Hinton et al., 2011) and propose our Graph Capsule Network (GCAPS-CNN) model. In addition, we… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 45 times. VIEW TWEETS

References

Publications referenced by this paper.
Showing 1-10 of 40 references

Transforming Auto-Encoders

View 8 Excerpts
Highly Influenced

Weisfeiler-Lehman Graph Kernels

View 7 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…