English

Analyzing Neural Networks Based on Random Graphs

Machine Learning 2020-12-03 v3 Computer Vision and Pattern Recognition Neurons and Cognition Machine Learning

Abstract

We perform a massive evaluation of neural networks with architectures corresponding to random graphs of various types. We investigate various structural and numerical properties of the graphs in relation to neural network test accuracy. We find that none of the classical numerical graph invariants by itself allows to single out the best networks. Consequently, we introduce a new numerical graph characteristic that selects a set of quasi-1-dimensional graphs, which are a majority among the best performing networks. We also find that networks with primarily short-range connections perform better than networks which allow for many long-range connections. Moreover, many resolution reducing pathways are beneficial. We provide a dataset of 1020 graphs and the test accuracies of their corresponding neural networks at https://github.com/rmldj/random-graph-nn-paper

Keywords

Cite

@article{arxiv.2002.08104,
  title  = {Analyzing Neural Networks Based on Random Graphs},
  author = {Romuald A. Janik and Aleksandra Nowak},
  journal= {arXiv preprint arXiv:2002.08104},
  year   = {2020}
}

Comments

Added new results and discussion

R2 v1 2026-06-23T13:46:38.229Z