Graph neural networks (GNNs) emerged recently as a standard toolkit for learning from data on graphs. Current GNN designing works depend on immense human expertise to explore different message-passing mechanisms, and require manual enumeration to determine the proper message-passing depth. Inspired by the strong searching capability of neural architecture search (NAS) in CNN, this paper proposes Graph Neural Architecture Search (GNAS) with novel-designed search space. The GNAS can automatically learn better architecture with the optimal depth of message passing on the graph. Specifically, we design Graph Neural Architecture Paradigm (GAP) with tree-topology computation procedure and two types of fine-grained atomic operations (feature filtering and neighbor aggregation) from message-passing mechanism to construct powerful graph network search space. Feature filtering performs adaptive feature selection, and neighbor aggregation captures structural information and calculates neighbors' statistics. Experiments show that our GNAS can search for better GNNs with multiple message-passing mechanisms and optimal message-passing depth. The searched network achieves remarkable improvement over state-of-the-art manual designed and search-based GNNs on five large-scale datasets at three classical graph tasks. Codes can be found at https://github.com/phython96/GNAS-MP.
翻译:最近,GNN设计工作依靠巨大的人类专门知识来探索不同的信息传递机制,并需要人工查点以确定适当的信息传递深度。在CNN神经结构搜索(NAS)的强大搜索能力激励下,本文建议借助新设计的搜索空间来搜索神经结构搜索(GNAS) 。GNAS 能够自动学习更好的架构,其信息传递到图表上的最佳深度。具体地说,我们设计了具有树型计算程序和两种精细的原子操作(功能过滤和邻居聚合)的神经结构图(GAP),以探索不同的信息传递机制,并需要人工查点以确定适当的信息传递深度。受CNNPN(NAS)神经结构搜索(NAS)的强大搜索能力所启发,本文建议用新设计的搜索空间来搜索神经结构搜索(GNAS ) 。 实验显示,我们的GNAS可以用多个信息传递机制以及最佳信息传递深度来搜索更好的GNNS。我们搜索的网络在S-art 和两种精细的智能原子操作器上取得了显著的改进。在GNNS/MSDS上设计了五个大型的GNAS/搜索任务。