Classification in Networked Data with Heterophily

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="236769.fig.001a" src="https://static.hindawi.com/articles/tswj/volume-2013/236769/figures/236769.fig.001a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>Texas</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="236769.fig.001b" src="https://static.hindawi.com/articles/tswj/volume-2013/236769/figures/236769.fig.001b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>Cornell</td></tr></table></td></tr><tr class="fig-image" id="c"><td><img alt="236769.fig.001c" src="https://static.hindawi.com/articles/tswj/volume-2013/236769/figures/236769.fig.001c.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(c) </b> Wisconsin</td></tr></table></td></tr><tr class="fig-image" id="d"><td><img alt="236769.fig.001d" src="https://static.hindawi.com/articles/tswj/volume-2013/236769/figures/236769.fig.001d.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(d) </b> Washington</td></tr></table></td></tr><tr class="fig-image" id="e"><td><img alt="236769.fig.001e" src="https://static.hindawi.com/articles/tswj/volume-2013/236769/figures/236769.fig.001e.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(e) </b> Citeseer</td></tr></table></td></tr><tr class="fig-image" id="f"><td><img alt="236769.fig.001f" src="https://static.hindawi.com/articles/tswj/volume-2013/236769/figures/236769.fig.001f.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(f) </b>Cora</td></tr></table></td></tr></table>

<table>Results of comparison experiments.</table>

The Scientific World Journal

fig1

Figure 1

Figure 1: Classification in Networked Data with Heterophily 