
On the Transferability of Spectral Graph Filters
This paper focuses on spectral filters on graphs, namely filters defined...
01/29/2019 ∙ by Ron Levie, et al. ∙ 0 ∙ shareread it

Stationary signal processing on graphs
Graphs are a central tool in machine learning and information processing...
01/11/2016 ∙ by Nathanaël Perraudin, et al. ∙ 0 ∙ shareread it

Graph Neural Networks with convolutional ARMA filters
Recent graph neural networks implement convolutional layers based on pol...
01/05/2019 ∙ by Filippo Maria Bianchi, et al. ∙ 0 ∙ shareread it

Graph Neural Networks with distributed ARMA filters
Recent graph neural networks implement convolutional layers based on pol...
01/05/2019 ∙ by Filippo Maria Bianchi, et al. ∙ 0 ∙ shareread it

Machine Learning for QoT Estimation of Unseen Optical Network States
We apply deep graph convolutional neural networks for QualityofTransmi...
12/18/2018 ∙ by Tania Panayiotou, et al. ∙ 0 ∙ shareread it

GraphFlow: A New Graph Convolutional Network Based on Parallel Flows
In view of the huge success of convolution neural networks (CNN) for ima...
02/25/2019 ∙ by Feng Ji, et al. ∙ 0 ∙ shareread it

Learning Local Receptive Fields and their Weight Sharing Scheme on Graphs
We propose a simple and generic layer formulation that extends the prope...
06/08/2017 ∙ by JeanCharles Vialatte, et al. ∙ 0 ∙ shareread it
Transferability of Spectral Graph Convolutional Neural Networks
This paper focuses on spectral graph convolutional neural networks (ConvNets), where filters are defined as elementwise multiplication in the frequency domain of a graph. In machine learning settings where the dataset consists of signals defined on many different graphs, the trained ConvNet should generalize to signal on graphs unseen in the training set. It is thus important to transfer filters from one graph to the other. Transferability, which is a certain type of generalization capability, can be loosely defined as follows: if two graphs describe the same phenomenon, then a single filter/ConvNet should have similar repercussions on both graphs. This paper aims at debunking the common misconception that spectral filters are not transferable. We show that if two graphs discretize the same continuous metric space, then a spectral filter/ConvNet has approximately the same repercussion on both graphs. Our analysis is more permissive than the standard analysis. Transferability is typically described as the robustness of the filter to small graph perturbations and reindexing of the vertices. Our analysis accounts also for large graph perturbations. We prove transferability between graphs that can have completely different dimensions and topologies, only requiring that both graphs discretize the same underlying continuous space.
READ FULL TEXT