34adeb8e3242824038aa65460a47c29e-Supplemental.pdf

For notation simplicity, GNNF here is considered in GNTK format. The weights ofF, φ is i.i.d. Let ha,bi denote inner-product of vectoraandb. Next,weexperimentally verify the necessity of training locally specialized NeighGen. Specifically, we present theL2 distance between the averaged feature distributions of neighborhoods from these three types of graphs to show how the NeighGen generated missing neighborsnarrowthegap.