Watch Your Step: Learning Graph Embeddings Through Attention

@article{AbuElHaija2017WatchYS,
  title={Watch Your Step: Learning Graph Embeddings Through Attention},
  author={Sami Abu-El-Haija and Bryan Perozzi and Rami Al-Rfou' and Alex Alemi},
  journal={CoRR},
  year={2017},
  volume={abs/1710.09599}
}
Graph embedding methods represent nodes in a continuous vector space, preserving information from the graph (e.g. by sampling random walks). There are many hyper-parameters to these methods (such as random walk length) which have to be manually tuned for every graph. In this paper, we replace random walk hyperparameters with trainable parameters that we automatically learn via backpropagation. In particular, we learn a novel attention model on the power series of the transition matrix, which… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 17 times over the past 90 days. VIEW TWEETS

From This Paper

Figures, tables, results, connections, and topics extracted from this paper.
6 Extracted Citations
32 Extracted References
Similar Papers

Similar Papers

Loading similar papers…