UPS: optimizing Undirected Positive Sparse graph for neural graph filtering

Mikhail Yurochkin, Dung Thai, Hung Hai Bui, XuanLong Nguyen

Feb 15, 2018 (modified: Feb 15, 2018) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: In this work we propose a novel approach for learning graph representation of the data using gradients obtained via backpropagation. Next we build a neural network architecture compatible with our optimization approach and motivated by graph filtering in the vertex domain. We demonstrate that the learned graph has richer structure than often used nearest neighbors graphs constructed based on features similarity. Our experiments demonstrate that we can improve prediction quality for several convolution on graphs architectures, while others appeared to be insensitive to the input graph.
  • TL;DR: Graph Optimization with signal filtering in the vertex domain.