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.
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}
}