NC-GNN: Consistent Neighbors of Nodes Help More in Graph Neural Networks

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2022/8641220/figures/8641220.fig.003a.svgz" name="8641220.fig.003a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Samples in Cora</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2022/8641220/figures/8641220.fig.003b.svgz" name="8641220.fig.003b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Samples in Citeseer</td></tr></table>

<div>Sampled predicted low neighbor consistency nodes in datasets. Numbers included are the node index, and different color indicates different class.</div>

Wireless Communications and Mobile Computing

fig3

Figure 3

Figure 3: NC-GNN: Consistent Neighbors of Nodes Help More in Graph Neural Networks 