The success of deep convolutional neural networks in the domains of computer vision and
speech recognition has led researchers to investigate generalizations of the said
architecture to graph-structured data. A recently-proposed method called Graph
Convolutional Networks has been able to achieve state-of-the-art results in the task of node
classification. However, since the proposed method relies on localized first-order
approximations of spectral graph convolutions, it is unable to capture higher-order …

Various embodiments describe techniques for making infer ences from graph-structured
data using graph convolutional networks (GCNs). The GCNs use various pre-defined motifs
to filter and select adjacent nodes for graph convolution at individual nodes, rather than
merely using edge-defined immediate-neighbor adjacency for information integration at
each node. In certain embodiments, the graph convolu tional networks use attention
mechanisms to select a motif from multiple motifs and select a step size for each respec tive …