论文标题
路径：带随机路径采样的空间图注意神经网络
PathSAGE: Spatial Graph Attention Neural Networks With Random Path Sampling
论文作者
论文摘要
Graph卷积网络（GCN）最近在非欧几里得结构数据处理方面取得了巨大成功。在现有研究中，CCN中使用了更深层的层来提取欧几里得结构数据的更深特征。但是，对于非欧几里得结构数据，太深的GCN会面临“邻居爆炸”和“过度平滑光滑”之类的问题，也不能应用于大型数据集。为了解决这些问题，我们提出了一个称为“路径”的模型，该模型可以通过扩展接受场来学习高阶拓扑信息并改善模型的性能。该模型从中央节点开始随机采样路径，并通过变压器编码将其聚合。路径只有一层结构来汇总节点，可以避免上面的这些问题。评估结果表明，我们的模型与归纳学习任务中最先进的模型实现了可比的性能。
Graph Convolutional Networks (GCNs) achieve great success in non-Euclidean structure data processing recently. In existing studies, deeper layers are used in CCNs to extract deeper features of Euclidean structure data. However, for non-Euclidean structure data, too deep GCNs will confront with problems like "neighbor explosion" and "over-smoothing", it also cannot be applied to large datasets. To address these problems, we propose a model called PathSAGE, which can learn high-order topological information and improve the model's performance by expanding the receptive field. The model randomly samples paths starting from the central node and aggregates them by Transformer encoder. PathSAGE has only one layer of structure to aggregate nodes which avoid those problems above. The results of evaluation shows that our model achieves comparable performance with the state-of-the-art models in inductive learning tasks.
