pith. sign in

arxiv: 1905.10224 · v1 · pith:C5AKPA7Hnew · submitted 2019-05-24 · 💻 cs.LG · cs.DM· cs.NA· cs.NE· math.NA· stat.ML

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

classification 💻 cs.LG cs.DMcs.NAcs.NEmath.NAstat.ML
keywords graphsconvolutionaldatasetsgraphhypergraphlow-ranknetworksnon-sparse
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.