← Search

Elisabetta Ghisu

1 accepted papers

2019

Wasserstein Weisfeiler-Lehman Graph Kernels

NeurIPS 2019spotlight

Most graph kernels are an instance of the class of R-Convolution kernels, which measure the similarity of objects by comparing their substructures. Despite their empirical success, most graph kernels use a naive aggregation of the final set of substructures, usually a sum or average, thereby potenti…