1 code implementation • 5 May 2024 • Samuel Rey, Hamed Ajorlou, Gonzalo Mateos
We develop a novel convolutional architecture tailored for learning from data defined over directed acyclic graphs (DAGs).
no code implementations • 22 Mar 2024 • Madeline Navarro, Samuel Rey, Andrei Buciulea, Antonio G. Marques, Santiago Segarra
We consider fair network topology inference from nodal observations.
1 code implementation • 11 Dec 2023 • Victor M. Tenorio, Samuel Rey, Antonio G. Marques
Graph Neural Networks (GNNs) have emerged as a notorious alternative to address learning problems dealing with non-Euclidean datasets.
no code implementations • 16 Sep 2023 • Victor M. Tenorio, Samuel Rey, Antonio G. Marques
Blind deconvolution over graphs involves using (observed) output graph signals to obtain both the inputs (sources) as well as the filter that drives (models) the graph diffusion process.
no code implementations • 30 Jun 2023 • Madeline Navarro, Samuel Rey, Andrei Buciulea, Antonio G. Marques, Santiago Segarra
We investigate the increasingly prominent task of jointly inferring multiple networks from nodal observations.
no code implementations • 26 Feb 2023 • Samuel Rey
With classical techniques facing troubles to deal with the irregular (non-Euclidean) domain where the signals are defined, a popular approach at the heart of graph signal processing (GSP) is to: (i) represent the underlying support via a graph and (ii) exploit the topology of this graph to process the signals at hand.
1 code implementation • 4 Dec 2022 • Samuel Rey, Madeline Navarro, Andrei Buciulea, Santiago Segarra, Antonio G. Marques
Motivated by this, we propose a joint graph learning method that takes into account the presence of hidden (latent) variables.
1 code implementation • 16 Oct 2022 • Samuel Rey, Victor M. Tenorio, Antonio G. Marques
Different from existing works, we formulate a non-convex optimization problem that operates in the vertex domain and jointly performs GF identification and graph denoising.
no code implementations • 11 Jul 2022 • Samuel Rey, T. Mitchell Roddenberry, Santiago Segarra, Antonio G. Marques
Guided by this, we first assume that we have a reference graph that is related to the sought graph (in the sense of having similar motif densities) and then, we exploit this relation by incorporating a similarity constraint and a regularization term in the network topology inference optimization problem.
1 code implementation • 5 Oct 2021 • Samuel Rey, Andrei Buciulea, Madeline Navarro, Santiago Segarra, Antonio G. Marques
Learning graphs from sets of nodal observations represents a prominent problem formally known as graph topology inference.
1 code implementation • 2 Oct 2021 • Victor M. Tenorio, Samuel Rey, Fernando Gama, Santiago Segarra, Antonio G. Marques
Graph convolutional neural networks (GCNNs) are popular deep learning architectures that, upon replacing regular convolutions with graph filters (GFs), generalize CNNs to irregular domains.
1 code implementation • 24 Sep 2021 • Samuel Rey, Santiago Segarra, Reinhard Heckel, Antonio G. Marques
This paper introduces two untrained graph neural network architectures for graph signal denoising, provides theoretical guarantees for their denoising capabilities in a simple setup, and numerically validates the theoretical results in more general scenarios.
1 code implementation • 10 Mar 2021 • Samuel Rey, Antonio G. Marques
When approaching graph signal processing tasks, graphs are usually assumed to be perfectly known.
1 code implementation • 2 Aug 2019 • Samuel Rey, Antonio G. Marques, Santiago Segarra
While deep convolutional architectures have achieved remarkable results in a gamut of supervised applications dealing with images and speech, recent works show that deep untrained non-convolutional architectures can also outperform state-of-the-art methods in several tasks such as image compression and denoising.