2 papers
cs.LG2019
Wasserstein Weisfeiler-Lehman Graph Kernels
Matteo Togninalli, Elisabetta Ghisu, Felipe Llinares-López +2
Most graph kernels are an instance of the class of -Convolution kernels, which measure the similarity of objects by comparing their substructures. Despite their empiri…
cs.LG2018
Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
Bastian Rieck, Matteo Togninalli, Christian Bock +4
While many approaches to make neural networks more fathomable have been proposed, they are restricted to interrogating the network with input data. Measures for characterizing and…