Visiting Distant Neighbors in Graph Convolutional Networks
This work addresses data scarcity in graph learning for researchers, but it is incremental as it builds on existing methods.
The authors tackled the problem of limited labeled data in graph convolutional networks by extending neighbor inclusion to higher-order nodes, resulting in improved performance on citation graph datasets.
We extend the graph convolutional network method for deep learning on graph data to higher order in terms of neighboring nodes. In order to construct representations for a node in a graph, in addition to the features of the node and its immediate neighboring nodes, we also include more distant nodes in the calculations. In experimenting with a number of publicly available citation graph datasets, we show that this higher order neighbor visiting pays off by outperforming the original model especially when we have a limited number of available labeled data points for the training of the model.