Graph neural networks (GNNs) extend convolutional neural networks (CNNs) to graph-based data. A question that arises is how much performance improvement does the underlying graph structure in the GNN provide over the CNN (that ignores this graph structure). To address this question, we introduce edge entropy and evaluate how good an indicator it is for possible performance improvement of GNNs over CNNs. Our results on node classification with synthetic and real datasets show that lower values of edge entropy predict larger expected performance gains of GNNs over CNNs, and, conversely, higher edge entropy leads to expected smaller improvement gains.
@article{arxiv.2012.08698,
title = {Edge Entropy as an Indicator of the Effectiveness of GNNs over CNNs for Node Classification},
author = {Lavender Yao Jiang and John Shi and Mark Cheung and Oren Wright and José M. F. Moura},
journal= {arXiv preprint arXiv:2012.08698},
year = {2020}
}