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
翻译:我们对神经网络进行大规模评估,其结构与各种类型的随机图解相对应。我们调查图表与神经网络测试精确度有关的各种结构和数字属性。我们发现经典数字图的变异性本身都不允许单挑最佳网络。因此,我们引入了一个新的数字图特性,选择了一套准一维图,这些图解在最优秀的网络中占大多数。我们还发现,主要具有短距离连接的网络比允许许多远程连接的网络运行得更好。此外,许多分辨率减少路径也是有益的。我们在 https://github.com/rmldj/random-graph-nn-paper 上提供了1020个图表的数据集及其相应的神经网络的测试精度。我们提供了1020个图表的数据集和相应的神经网络的测试精度。