Kriging Convolutional Networks
Kriging Convolutional Networks
复制标题
DOI：
10.1609/aaai.v34i04.5716
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
G. Appleby;Linfeng Liu;Liping Liu
中科院分区：
文献类型：
--
作者：
G. Appleby;Linfeng Liu;Liping Liu
空间插值是一类估计问题，其中具有已知值的位置用于估计其他位置的值，重点是利用空间局部性和趋势。传统的克里金方法具有很强的高斯假设，因此通常无法捕捉数据中的复杂性。受图神经网络最新进展的启发，我们引入了Kriging卷积网络（KCN），这是一种结合图神经网络（GNN）和Kriging优点的方法。与标准GNN相比，KCN在生成预测时直接使用相邻观测值。KCN还包含克里金法作为特定配置。从经验上讲，我们证明了该模型在几个应用中优于GNNs和克里金。
Spatial interpolation is a class of estimation problems where locations with known values are used to estimate values at other locations, with an emphasis on harnessing spatial locality and trends. Traditional kriging methods have strong Gaussian assumptions, and as a result, often fail to capture complexities within the data. Inspired by the recent progress of graph neural networks, we introduce Kriging Convolutional Networks (KCN), a method of combining advantages of Graph Neural Networks (GNN) and kriging. Compared to standard GNNs, KCNs make direct use of neighboring observations when generating predictions. KCNs also contain the kriging method as a specific configuration. Empirically, we show that this model outperforms GNNs and kriging in several applications.