• Levie

    Final published version, 302 KB, PDF document

This paper focuses on spectral filters on graphs, namely filters defined as elementwise multiplication in the frequency domain of a graph. In many graph signal processing settings, it is important to transfer a filter from one graph to another. One example is in graph convolutional neural networks (ConvNets), where the dataset consists of signals defined on many different graphs, and the learned filters should generalize to signals on new graphs, not present in the training set. A necessary condition for transferability (the ability to transfer filters) is stability. Namely, given a graph filter, if we add a small perturbation to the graph, then the filter on the perturbed graph is a small perturbation of the original filter. It is a common misconception that spectral filters are not stable, and this paper aims at debunking this mistake. We introduce a space of filters, called the Cayley smoothness space, that contains the filters of state-of-the-art spectral filtering methods, and whose filters can approximate any generic spectral filter. For filters in this space, the perturbation in the filter is bounded by a constant times the perturbation in the graph, and filters in the Cayley smoothness space are thus termed linearly stable. By combining stability with the known property of equivariance, we prove that graph spectral filters are transferable.
Original languageEnglish
Title of host publicationSampTa 2019: 13th International conference on Sampling Theory and Applications
Subtitle of host publicationBordeaux, France
EditorsArash Amini
Number of pages5
Publication statusPublished - 2019
EventSampTa 2019: 13th International conference on Sampling Theory and Applications - Bordeaux, France
Duration: 8 Jul 201912 Jul 2019
Conference number: 13


ConferenceSampTa 2019: 13th International conference on Sampling Theory and Applications
Abbreviated titleSampTa 2019
Internet address

ID: 70194671