← Search

Matteo Togninalli

2 accepted papers

2019

Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology

ICLR 2019poster

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 monitoring structural properties, however, have not been developed. In this work, we propose neural persistence, a compl…

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…