English

Learning Graph While Training: An Evolving Graph Convolutional Neural Network

Machine Learning 2017-08-17 v1 Computer Vision and Pattern Recognition

Abstract

Convolution Neural Networks on Graphs are important generalization and extension of classical CNNs. While previous works generally assumed that the graph structures of samples are regular with unified dimensions, in many applications, they are highly diverse or even not well defined. Under some circumstances, e.g. chemical molecular data, clustering or coarsening for simplifying the graphs is hard to be justified chemically. In this paper, we propose a more general and flexible graph convolution network (EGCN) fed by batch of arbitrarily shaped data together with their evolving graph Laplacians trained in supervised fashion. Extensive experiments have been conducted to demonstrate the superior performance in terms of both the acceleration of parameter fitting and the significantly improved prediction accuracy on multiple graph-structured datasets.

Keywords

Cite

@article{arxiv.1708.04675,
  title  = {Learning Graph While Training: An Evolving Graph Convolutional Neural Network},
  author = {Ruoyu Li and Junzhou Huang},
  journal= {arXiv preprint arXiv:1708.04675},
  year   = {2017}
}

Comments

10 pages, submitted to NIPS 2017