9 citations · 25 across the 39 of their papers we have counts for
15 papers · 1 filter
GraphToolbox: A Configurable Python Framework for Graph Neural Network Forecasting
Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude +1
Electricity forecasting often involves spatially related signals observed over regions, substations, and feeders, and Graph Neural Networks (GNNs) provide a natural way to represen…
Dual-Criterion Curriculum Learning: Application to Temporal Data
Gaspard Abel, Eloi Campagne, Mohamed Benloughmari +1
Curriculum Learning (CL) is a meta-learning paradigm that trains a model by feeding the data instances incrementally according to a schedule, which is based on difficulty progressi…
Enhancing LIME using Neural Decision Trees
Mohamed Aymen Bouyahia, Argyris Kalogeratos
Interpreting complex machine learning models is a critical challenge, especially for tabular data where model transparency is paramount. Local Interpretable Model-Agnostic Explanat…
Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints
Gabriel Singer, Samuel Gruffaz, Olivier Vo Van +2
As acquiring reliable ground-truth labels is usually costly, or infeasible, crowdsourcing and aggregation of noisy human annotations is the typical resort. Aggregating subjective l…
Cascaded Transfer: Learning Many Tasks under Budget Constraints
Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude +2
In distributed applications, such as energy demand forecasting at the substation level or federated learning, a large number of related tasks must be learned by different models, w…
Multi-view diffusion geometry using intertwined diffusion trajectories
Gwendal Debaussart-Joniec, Argyris Kalogeratos
This paper introduces a comprehensive unified framework for constructing multi-view diffusion geometries through intertwined multi-view diffusion trajectories (MDTs), a class of in…
Graph Neural Networks for Electricity Load Forecasting
Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude +2
Forecasting electricity demand is increasingly challenging as energy systems become more decentralized and intertwined with renewable sources. Graph Neural Networks (GNNs) have rec…
Leveraging Graph Neural Networks to Forecast Electricity Consumption
Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude +1
Accurate electricity demand forecasting is essential for several reasons, especially as the integration of renewable energy sources and the transition to a decentralized network pa…
UniForCE: The Unimodality Forest Method for Clustering and Estimation of the Number of Clusters
Georgios Vardakas, Argyris Kalogeratos, Aristidis Likas
Estimating the number of clusters k while clustering the data is a challenging task. An incorrect cluster assumption indicates that the number of clusters k gets wrongly estimated.…
To tree or not to tree? Assessing the impact of smoothing the decision boundaries
Anthea Mérida, Argyris Kalogeratos, Mathilde Mougeot
When analyzing a dataset, it can be useful to assess how smooth the decision boundaries need to be for a model to better fit the data. This paper addresses this question by proposi…
Parametrized Power-Iteration Clustering for Directed Graphs
Gwendal Debaussart-Joniec, Harry Sevi, Matthieu Jonckheere +1
Vertex-level clustering for directed graphs (digraphs) remains challenging as edge directionality breaks the key assumptions underlying popular spectral methods, which also incur t…
Model family selection for classification using Neural Decision Trees
Anthea Mérida Montes de Oca, Argyris Kalogeratos, Mathilde Mougeot
Model selection consists in comparing several candidate models according to a metric to be optimized. The process often involves a grid search, or such, and cross-validation, which…
Offline detection of change-points in the mean for stationary graph signals
Alejandro de la Concha, Nicolas Vayatis, Argyris Kalogeratos
This paper addresses the problem of segmenting a stream of graph signals: we aim to detect changes in the mean of a multivariate signal defined over the nodes of a known graph. We…
Revealing posturographic features associated with the risk of falling in patients with Parkinsonian syndromes via machine learning
Ioannis Bargiotas, Argyris Kalogeratos, Myrto Limnios +3
Falling in Parkinsonian syndromes (PS) is associated with postural instability and consists a common cause of disability among PS patients. Current posturographic practices record…
A Probabilistic Framework to Node-level Anomaly Detection in Communication Networks
Batiste Le Bars, Argyris Kalogeratos
In this paper we consider the task of detecting abnormal communication volume occurring at node-level in communication networks. The signal of the communication activity is modeled…