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.

Graphs have been widely used in data mining and machine learning due to their unique representation of real-world objects and their interactions.

Referring to Section 4.3, FedSage+ includes two phases. We describe the aggregation operation below. We are going to define the kernel matrix of two nodes u,v V as follows. B.1 needs to calculate 1) a covariance matrix In Graphsage, this is equivalent to having K graph convectional layers. 's derivative is denoted as The generalization ability in the NTK regime and depends on the kernel matrix.