Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such as high computational cost and optimization difficulty. More importantly, previous NAS methods have ignored the uniqueness of GNNs, where GNNs possess expressive power without training. With the randomly-initialized weights, we can then seek the optimal architecture parameters via the sparse coding objective and derive a novel NAS-GNNs method, namely neural architecture coding (NAC). Consequently, our NAC holds a no-update scheme on GNNs and can efficiently compute in linear time. Empirical evaluations on multiple GNN benchmark datasets demonstrate that our approach leads to state-of-the-art performance, which is up to $200\times$ faster and $18.8\%$ more accurate than the strong baselines.

翻译：面向图神经网络（GNN）的神经架构搜索（NAS-GNNs）已取得显著优于人工设计架构的性能。然而，这些方法继承了传统NAS方法的固有缺陷，如高计算代价与优化困难。更关键的是，既有NAS方法忽视了GNN的特殊性——GNN在未经训练时即具备表达能力。基于随机初始化的权重，我们可通过稀疏编码目标函数寻求最优架构参数，由此提出新型NAS-GNNs方法——神经架构编码（NAC）。该方法在GNN上采用免更新机制，能够以线性时间复杂度高效计算。在多个GNN基准数据集上的实验表明，我们的方法取得了当前最优性能，相比强基线方法速度提升高达200倍，准确率提高18.8%。