Deep learning with graph convolutional networks: An overview and latest applications in computational intelligence
Convolutional neural networks (CNNs) have received widespread attention due to their
powerful modeling capabilities and have been successfully applied in natural language …
powerful modeling capabilities and have been successfully applied in natural language …
Graph Laplacian mixture model
HP Maretic, P Frossard - IEEE Transactions on Signal and …, 2020 - ieeexplore.ieee.org
Graph learning methods have recently been receiving increasing interest as means to infer
structure in datasets. Most of the recent approaches focus on different relationships between …
structure in datasets. Most of the recent approaches focus on different relationships between …
[HTML][HTML] Dynamics of functional network organization through graph mixture learning
Understanding the organizational principles of human brain activity at the systems level
remains a major challenge in network neuroscience. Here, we introduce a fully data-driven …
remains a major challenge in network neuroscience. Here, we introduce a fully data-driven …
Mask combination of multi-layer graphs for global structure inference
Structure inference is an important task for network data processing and analysis in data
science. In recent years, quite a few approaches have been developed to learn the graph …
science. In recent years, quite a few approaches have been developed to learn the graph …
Annihilation Filter Approach for Estimating Graph Dynamics from Diffusion Processes
A Venkitaraman, P Frossard - ICASSP 2022-2022 IEEE …, 2022 - ieeexplore.ieee.org
We propose an approach for estimating graph diffusion processes using annihilation filters
from a finite set of observations of the diffusion process made at regular intervals. Our …
from a finite set of observations of the diffusion process made at regular intervals. Our …
Representing graphs through data with learning and optimal transport
H Petric Maretic - 2021 - infoscience.epfl.ch
Graphs offer a simple yet meaningful representation of relationships between data. This
representation is often used in machine learning algorithms in order to incorporate structural …
representation is often used in machine learning algorithms in order to incorporate structural …