Probabilistic and Regularized Graph Convolutional Networks
Machine Learning
2018-03-14 v1 Machine Learning
Abstract
This paper explores the recently proposed Graph Convolutional Network architecture proposed in (Kipf & Welling, 2016) The key points of their work is summarized and their results are reproduced. Graph regularization and alternative graph convolution approaches are explored. I find that explicit graph regularization was correctly rejected by (Kipf & Welling, 2016). I attempt to improve the performance of GCN by approximating a k-step transition matrix in place of the normalized graph laplacian, but I fail to find positive results. Nonetheless, the performance of several configurations of this GCN variation is shown for the Cora, Citeseer, and Pubmed datasets.
Keywords
Cite
@article{arxiv.1803.04489,
title = {Probabilistic and Regularized Graph Convolutional Networks},
author = {Sean Billings},
journal= {arXiv preprint arXiv:1803.04489},
year = {2018}
}