Semi-Supervised Classification on Non-Sparse Graphs Using Low-Rank Graph Convolutional Networks
This addresses efficiency issues for researchers and practitioners working with large graph-based datasets, though it appears incremental as it builds on existing GCN methods.
The paper tackles the problem of high computational cost in training Graph Convolutional Networks (GCNs) on large non-sparse graphs by introducing low-rank filters, resulting in significant runtime acceleration and improved accuracy.
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.