A theoretical performance analysis of the graph neural network (GNN) is presented. For classification tasks, the neural network approach has the advantage in terms of flexibility that it can be employed in a data-driven manner, whereas Bayesian inference requires the assumption of a specific model. A fundamental question is then whether GNN has a high accuracy in addition to this flexibility. Moreover, whether the achieved performance is predominately a result of the backpropagation or the architecture itself is a matter of considerable interest. To gain a better insight into these questions, a mean-field theory of a minimal GNN architecture is developed for the graph partitioning problem. This demonstrates a good agreement with numerical experiments.
@article{arxiv.1810.11908,
title = {Mean-field theory of graph neural networks in graph partitioning},
author = {Tatsuro Kawamoto and Masashi Tsubaki and Tomoyuki Obuchi},
journal= {arXiv preprint arXiv:1810.11908},
year = {2020}
}
Comments
16 pages, 6 figures, Thirty-second Conference on Neural Information Processing Systems (NIPS2018)