论文标题
基于随机图分析神经网络
Analyzing Neural Networks Based on Random Graphs
论文作者
论文摘要
我们对与各种类型的随机图相对应的架构进行了大量评估。我们研究了图与神经网络测试准确性的各种结构和数值特性。我们发现，没有一个经典的数字图形不变式本身允许挑选出最佳的网络。因此，我们引入了一个新的数值图特性，该特征选择一组准1维图，这是最佳性能网络中的多数。我们还发现，主要是短距离连接的网络的性能优于网络，该网络允许许多远程连接。此外，许多减少途径的分辨率都是有益的。我们提供1020个图的数据集及其相应神经网络的测试精度，网址为https://github.com/rmldj/random-graph-nn-paper
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
