69 citations · 200 across the 21 of their papers we have counts for
23 papers
Network-Wide Traffic Volume Estimation from Speed Profiles using a Spatio-Temporal Graph Neural Network with Directed Spatial Attention
Léo Hein, Giovanni de Nunzio, Giovanni Chierchia +2
Existing traffic volume estimation methods typically address either forecasting traffic on sensor-equipped roads or spatially imputing missing volumes using nearby sensors. While f…
Clustering Dynamics for Improved Speed Prediction Deriving from Topographical GPS Registrations
Sarah Almeida Carneiro, Giovanni Chierchia, Aurelie Pirayre +1
A persistent challenge in the field of Intelligent Transportation Systems is to extract accurate traffic insights from geographic regions with scarce or no data coverage. To this e…
SWMLP: Shared Weight Multilayer Perceptron for Car Trajectory Speed Prediction using Road Topographical Features
Sarah Almeida Carneiro, Giovanni Chierchia, Jean Charléty +2
Although traffic is one of the massively collected data, it is often only available for specific regions. One concern is that, although there are studies that give good results for…
Domain-Aware Augmentations for Unsupervised Online General Continual Learning
Nicolas Michel, Romain Negrel, Giovanni Chierchia +1
Continual Learning has been challenging, especially when dealing with unsupervised scenarios such as Unsupervised Online General Continual Learning (UOGCL), where the learning agen…
New metrics for analyzing continual learners
Nicolas Michel, Giovanni Chierchia, Romain Negrel +2
Deep neural networks have shown remarkable performance when trained on independent and identically distributed data from a fixed set of classes. However, in real-world scenarios, i…
Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning
Nicolas Michel, Giovanni Chierchia, Romain Negrel +1
We use the maximum a posteriori estimation principle for learning representations distributed on the unit sphere. We propose to use the angular Gaussian distribution, which corresp…
Contrastive Learning for Online Semi-Supervised General Continual Learning
Nicolas Michel, Romain Negrel, Giovanni Chierchia +1
We study Online Continual Learning with missing labels and propose SemiCon, a new contrastive loss designed for partly labeled data. We demonstrate its efficiency by devising a mem…
FGOT: Graph Distances based on Filters and Optimal Transport
Hermina Petric Maretic, Mireille El Gheche, Giovanni Chierchia +1
Graph comparison deals with identifying similarities and dissimilarities between graphs. A major obstacle is the unknown alignment of graphs, as well as the lack of accurate and in…
DeConFuse : A Deep Convolutional Transform based Unsupervised Fusion Framework
Pooja Gupta, Jyoti Maggu, Angshul Majumdar +2
This work proposes an unsupervised fusion framework based on deep convolutional transform learning. The great learning ability of convolutional filters for data analysis is well ac…
ConFuse: Convolutional Transform Learning Fusion Framework For Multi-Channel Data Analysis
Pooja Gupta, Jyoti Maggu, Angshul Majumdar +2
This work addresses the problem of analyzing multi-channel time series data %. In this paper, we by proposing an unsupervised fusion framework based on %the recently proposed convo…
Deep Convolutional Transform Learning -- Extended version
Jyoti Maggu, Angshul Majumdar, Emilie Chouzenoux +1
This work introduces a new unsupervised representation learning technique called Deep Convolutional Transform Learning (DCTL). By stacking convolutional transforms, our approach is…
Wasserstein-based Graph Alignment
Hermina Petric Maretic, Mireille El Gheche, Matthias Minder +2
We propose a novel method for comparing non-aligned graphs of different sizes, based on the Wasserstein distance between graph signal distributions induced by the respective graph…
GOT: An Optimal Transport framework for Graph comparison
Hermina Petric Maretic, Mireille EL Gheche, Giovanni Chierchia +1
We present a novel framework based on optimal transport for the challenging problem of comparing graphs. Specifically, we exploit the probabilistic distribution of smooth graph sig…
Ultrametric Fitting by Gradient Descent
Giovanni Chierchia, Benjamin Perret
We study the problem of fitting an ultrametric distance to a dissimilarity graph in the context of hierarchical cluster analysis. Standard hierarchical clustering methods are speci…
Stochastic Gradient Descent for Spectral Embedding with Implicit Orthogonality Constraint
Mireille El Gheche, Giovanni Chierchia, Pascal Frossard
In this paper, we propose a scalable algorithm for spectral embedding. The latter is a standard tool for graph clustering. However, its computational bottleneck is the eigendecompo…
OrthoNet: Multilayer Network Data Clustering
Mireille El Gheche, Giovanni Chierchia, Pascal Frossard
Network data appears in very diverse applications, like biological, social, or sensor networks. Clustering of network nodes into categories or communities has thus become a very co…
A Two-Stage Subspace Trust Region Approach for Deep Neural Network Training
Viacheslav Dudar, Giovanni Chierchia, Emilie Chouzenoux +2
In this paper, we develop a novel second-order method for training feed-forward neural nets. At each iteration, we construct a quadratic approximation to the cost function in a low…
A Random Block-Coordinate Douglas-Rachford Splitting Method with Low Computational Complexity for Binary Logistic Regression
Luis M. Briceno-Arias, Giovanni Chierchia, Emilie Chouzenoux +1
In this paper, we propose a new optimization algorithm for sparse logistic regression based on a stochastic version of the Douglas-Rachford splitting method. Our algorithm sweeps t…
SAR image despeckling through convolutional neural networks
G. Chierchia, D. Cozzolino, G. Poggi +1
In this paper we investigate the use of discriminative model learning through Convolutional Neural Networks (CNNs) for SAR image despeckling. The network uses a residual learning s…
Proximity Operators of Discrete Information Divergences
Mireille El Gheche, Giovanni Chierchia, Jean-Christophe Pesquet
Information divergences allow one to assess how close two distributions are from each other. Among the large panel of available measures, a special attention has been paid to conve…
A Proximal Approach for Sparse Multiclass SVM
G. Chierchia, Nelly Pustelnik, Jean-Christophe Pesquet +1
Sparsity-inducing penalties are useful tools to design multiclass support vector machines (SVMs). In this paper, we propose a convex optimization approach for efficiently and exact…
A Non-Local Structure Tensor Based Approach for Multicomponent Image Recovery Problems
Giovanni Chierchia, Nelly Pustelnik, Beatrice Pesquet-Popescu +1
Non-Local Total Variation (NLTV) has emerged as a useful tool in variational methods for image recovery problems. In this paper, we extend the NLTV-based regularization to multicom…
Epigraphical splitting for solving constrained convex formulations of inverse problems with proximal tools
Giovanni Chierchia, Nelly Pustelnik, Jean-Christophe Pesquet +1
We propose a proximal approach to deal with a class of convex variational problems involving nonlinear constraints. A large family of constraints, proven to be effective in the sol…