… We introduce a novel kernel that upgrades the Weisfeiler-Lehman and other graph kernels
… the commonalities between graph kernels like the Weisfeiler-Lehman graph kernel (WLGK) […

… Given a subgraph GS induced by the set of vertices S, the kernel computes a graph invariant
encoding for the subgraph via a label function lg : G → Σ∗, where G is the set of rooted …

… All graph invariants of two graphs have … graphs: We will show next that graph kernels are
an answer to this problem. To understand the contribution of graph kernels to the field of graph …

… the ability of graph kernels to distinguish the graphs in common … a Gaussian RBF kernel with
the metric induced by a graph kernel in … is that if the kernels on substructures are invariant to …

… to a kernel that is invariant with respect to the graph structure it is meant to measure. In this
case, the unnormalized adjacency matrix A (which simply counts random walks instead of …

… But, if both of them are of identical size, we have to resort to graph invariants. These are
computationally more expensive, like the shortest path length which has a cubic runtime …

… Permutation invariance has proved to be the central constraint around … graph kernels literature
is organized, effectively stipulating that graph kernels must be built out of graph invariants. …

… invariants computed from the trace of the heat kernel can be used to characterize graphs for
the … Section 3, we develop the three sets of invariants deduced from graph heat kernel which …

… presents kernel regression as a novel unifying framework for graph signal reconstruction and
explores the implications of the so-called representer theorem. Kernel … -invariant kernels in …

… a reproducing kernel Hilbert space with shift-invariant kernel … reproducing kernel Hilbert
space with a shift-invariant kernel. … In Section IV, we introduce the concept of shift-invariant kernel…