A Unified Deep Learning Formalism For Processing Graph Signals

05/01/2019
by   Myriam Bontonou, et al.
0

Convolutional Neural Networks are very efficient at processing signals defined on a discrete Euclidean space (such as images). However, as they can not be used on signals defined on an arbitrary graph, other models have emerged, aiming to extend its properties. We propose to review some of the major deep learning models designed to exploit the underlying graph structure of signals. We express them in a unified formalism, giving them a new and comparative reading.

READ FULL TEXT

page 1

page 2

research
10/01/2019

Predicting Alzheimer's Disease by Hierarchical Graph Convolution from Positron Emission Tomography Imaging

Imaging-based early diagnosis of Alzheimer Disease (AD) has become an ef...
research
01/11/2016

Stationary signal processing on graphs

Graphs are a central tool in machine learning and information processing...
research
06/14/2023

Graph Laplacian Learning with Exponential Family Noise

A common challenge in applying graph machine learning methods is that th...
research
09/26/2022

PearNet: A Pearson Correlation-based Graph Attention Network for Sleep Stage Recognition

Sleep stage recognition is crucial for assessing sleep and diagnosing ch...
research
05/31/2022

Generalised Implicit Neural Representations

We consider the problem of learning implicit neural representations (INR...
research
05/25/2023

A graphon-signal analysis of graph neural networks

We present an approach for analyzing message passing graph neural networ...
research
01/07/2019

Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation

Convolutional Neural Networks (CNN) have been successful in processing d...

Please sign up or login with your details

Forgot password? Click here to reset