English

Semi-Supervised Classification on Non-Sparse Graphs Using Low-Rank Graph Convolutional Networks

Machine Learning 2019-05-27 v1 Discrete Mathematics Neural and Evolutionary Computing Numerical Analysis Machine Learning

Abstract

Graph Convolutional Networks (GCNs) have proven to be successful tools for semi-supervised learning on graph-based datasets. For sparse graphs, linear and polynomial filter functions have yielded impressive results. For large non-sparse graphs, however, network training and evaluation becomes prohibitively expensive. By introducing low-rank filters, we gain significant runtime acceleration and simultaneously improved accuracy. We further propose an architecture change mimicking techniques from Model Order Reduction in what we call a reduced-order GCN. Moreover, we present how our method can also be applied to hypergraph datasets and how hypergraph convolution can be implemented efficiently.

Keywords

Cite

@article{arxiv.1905.10224,
  title  = {Semi-Supervised Classification on Non-Sparse Graphs Using Low-Rank Graph Convolutional Networks},
  author = {Dominik Alfke and Martin Stoll},
  journal= {arXiv preprint arXiv:1905.10224},
  year   = {2019}
}
R2 v1 2026-06-23T09:22:19.398Z