Untrained graph neural networks for denoising
A fundamental problem in signal processing is to denoise a signal. While there are many
well-performing methods for denoising signals defined on regular domains, including …
well-performing methods for denoising signals defined on regular domains, including …
Overparametrized deep encoder-decoder schemes for inputs and outputs defined over graphs
There is a growing interest in the joint application of graph signal processing and neural
networks (NNs) for learning problems involving complex, non-linear and/or non-Euclidean …
networks (NNs) for learning problems involving complex, non-linear and/or non-Euclidean …
Node-variant graph filters in graph neural networks
Graph neural networks (GNNs) have been successfully employed in a myriad of applications
involving graph signals. Theoretical findings establish that GNNs use nonlinear activation …
involving graph signals. Theoretical findings establish that GNNs use nonlinear activation …
[HTML][HTML] Orbit entropy and symmetry index revisited
The size of the orbits or similar vertices of a network provides important information
regarding each individual component of the network. In this paper, we investigate the …
regarding each individual component of the network. In this paper, we investigate the …
[PDF][PDF] Orbit Entropy and Symmetry Index Revisited. Mathematics 2021, 9, 1086
The size of the orbits or similar vertices of a network provides important information
regarding each individual component of the network. In this paper, we investigate the …
regarding each individual component of the network. In this paper, we investigate the …