Search Results for author: Marco Corneli

Found 12 papers, 4 papers with code

Template based Graph Neural Network with Optimal Transport Distances

1 code implementation31 May 2022 Cédric Vincent-Cuaz, Rémi Flamary, Marco Corneli, Titouan Vayer, Nicolas Courty

Current Graph Neural Networks (GNN) architectures generally rely on two important components: node features embedding through message passing, and aggregation with a specialized form of pooling.

Graph Classification Graph Matching

Semi-relaxed Gromov-Wasserstein divergence with applications on graphs

1 code implementation6 Oct 2021 Cédric Vincent-Cuaz, Rémi Flamary, Marco Corneli, Titouan Vayer, Nicolas Courty

To this end, the Gromov-Wasserstein (GW) distance, based on Optimal Transport (OT), has proven to be successful in handling the specific nature of the associated objects.

Dictionary Learning

Semi-relaxed Gromov-Wasserstein divergence and applications on graphs

no code implementations ICLR 2022 Cédric Vincent-Cuaz, Rémi Flamary, Marco Corneli, Titouan Vayer, Nicolas Courty

To this end, the Gromov-Wasserstein (GW) distance, based on Optimal Transport (OT), has proven to be successful in handling the specific nature of the associated objects.

Dictionary Learning

Continuous Latent Position Models for Instantaneous Interactions

no code implementations31 Mar 2021 Riccardo Rastelli, Marco Corneli

We create a framework to analyse the timing and frequency of instantaneous interactions between pairs of entities.

Position

Online Graph Dictionary Learning

1 code implementation12 Feb 2021 Cédric Vincent-Cuaz, Titouan Vayer, Rémi Flamary, Marco Corneli, Nicolas Courty

Dictionary learning is a key tool for representation learning, that explains the data as linear combination of few basic elements.

Dictionary Learning Graph Classification +2

DeepLTRS: A Deep Latent Recommender System based on User Ratings and Reviews

no code implementations1 Jan 2021 Dingge LIANG, Marco Corneli, Pierre Latouche, Charles Bouveyron

The underlying motivation is that, when a user scores only a few products, the texts used in the reviews represent a significant source of information.

Recommendation Systems

An Optimal Control Approach to Learning in SIDARTHE Epidemic model

1 code implementation28 Oct 2020 Andrea Zugarini, Enrico Meloni, Alessandro Betti, Andrea Panizza, Marco Corneli, Marco Gori

We formulate the problem in terms of a functional risk that depends on the learning variables through the solutions of a dynamic system.

From text saliency to linguistic objects: learning linguistic interpretable markers with a multi-channels convolutional architecture

no code implementations7 Apr 2020 Laurent Vanni, Marco Corneli, Damon Mayaffre, Frédéric Precioso

A lot of effort is currently made to provide methods to analyze and understand deep neural network impressive performances for tasks such as image or text classification.

General Classification text-classification +1

Block modelling in dynamic networks with non-homogeneous Poisson processes and exact ICL

no code implementations10 Jul 2017 Marco Corneli, Pierre Latouche, Fabrice Rossi

We develop a model in which interactions between nodes of a dynamic network are counted by non homogeneous Poisson processes.

Exact ICL maximization in a non-stationary temporal extension of the stochastic block model for dynamic networks

no code implementations9 May 2016 Marco Corneli, Pierre Latouche, Fabrice Rossi

The stochastic block model (SBM) is a flexible probabilistic tool that can be used to model interactions between clusters of nodes in a network.

Stochastic Block Model

Modelling time evolving interactions in networks through a non stationary extension of stochastic block models

no code implementations8 Sep 2015 Marco Corneli, Pierre Latouche, Fabrice Rossi

To overcome this limitation, we propose a partition of the whole time horizon, in which interactions are observed, and develop a non stationary extension of the SBM, allowing to simultaneously cluster the nodes in a network along with fixed time intervals in which the interactions take place.

Clustering Stochastic Block Model

Exact ICL maximization in a non-stationary time extension of the latent block model for dynamic networks

no code implementations12 Jun 2015 Marco Corneli, Pierre Latouche, Fabrice Rossi

The latent block model (LBM) is a flexible probabilistic tool to describe interactions between node sets in bipartite networks, but it does not account for interactions of time varying intensity between nodes in unknown classes.

Cannot find the paper you are looking for? You can Submit a new open access paper.