36 citations · 75 across the 12 of their papers we have counts for
5 papers · 1 filter
Median activation functions for graph neural networks
Luana Ruiz, Fernando Gama, Antonio G. Marques +1
Graph neural networks (GNNs) have been shown to replicate convolutional neural networks' (CNNs) superior performance in many problems involving graphs. By replacing regular convolu…
Diffusion Scattering Transforms on Graphs
Fernando Gama, Alejandro Ribeiro, Joan Bruna
Stability is a key aspect of data analysis. In many applications, the natural notion of stability is geometric, as illustrated for example in computer vision. Scattering transforms…
Convolutional Neural Network Architectures for Signals Supported on Graphs
Fernando Gama, Antonio G. Marques, Geert Leus +1
Two architectures that generalize convolutional neural networks (CNNs) for the processing of signals supported on graphs are introduced. We start with the selection graph neural ne…
MIMO Graph Filters for Convolutional Neural Networks
Fernando Gama, Antonio G. Marques, Alejandro Ribeiro +1
Superior performance and ease of implementation have fostered the adoption of Convolutional Neural Networks (CNNs) for a wide array of inference and reconstruction tasks. CNNs impl…
Ergodicity in Stationary Graph Processes: A Weak Law of Large Numbers
Fernando Gama, Alejandro Ribeiro
For stationary signals in time the weak law of large numbers (WLLN) states that ensemble and realization averages are within e of each other with a probability of order O(1/Ne^2) w…