Learning Graph Representations with Embedding Propagation

@inproceedings{GarcaDurn2017LearningGR,
  title={Learning Graph Representations with Embedding Propagation},
  author={Alberto Garc{\'i}a-Dur{\'a}n and Mathias Niepert},
  booktitle={NIPS},
  year={2017}
}
We propose Embedding Propagation (EP), an unsupervised learning framework for graph-structured data. EP learns vector representations of graphs by passing two types of messages between neighboring nodes. Forward messages consist of label representations such as representations of words and other attributes associated with the nodes. Backward messages consist of gradients that result from aggregating the label representations and applying a reconstruction loss. Node representations are finally… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 4 times over the past 90 days. VIEW TWEETS
12 Citations
49 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 49 references

Large text compression benchmark

  • M. Mahoney
  • URL: http://www. mattmahoney. net/text/text. html
  • 2009
Highly Influential
5 Excerpts

Similar Papers

Loading similar papers…