514 citations
- Université d'Avignon et des Pays de VaucluseFR46 papers
- Centre National de la Recherche ScientifiqueFR15 papers
- Institut national de recherche en sciences et technologies du numériqueFR12 papers
- Nantes UniversitéFR12 papers
- Laboratoire des Sciences du Numérique de NantesFR10 papers
- EURECOMFR8 papers
- Le Mans UniversitéFR7 papers
- Centre Inria d'Université Côte d'AzurFR6 papers
- McGill UniversityCA6 papers
- National Institute of InformaticsJP6 papers
- Polytechnique MontréalCA6 papers
- University of CambridgeGB6 papers
8 papers · 1 filter
The distribution of calibrated likelihood functions on the probability-likelihood Aitchison simplex
Paul-Gauthier Noé, Andreas Nautsch, Driss Matrouf +2
While calibration of probabilistic predictions has been widely studied, this paper rather addresses calibration of likelihood functions. This has been discussed, especially in biom…
Pattern-Based Graph Classification: Comparison of Quality Measures and Importance of Preprocessing
Lucas Potin, Rosa Figueiredo, Vincent Labatut +1
Graph classification aims to categorize graphs based on their structural and attribute features, with applications in diverse fields such as social network analysis and bioinformat…
FedSV: Byzantine-Robust Federated Learning via Shapley Value
Khaoula Otmani, Rachid Elazouzi, Vincent Labatut
In Federated Learning (FL), several clients jointly learn a machine learning model: each client maintains a local model for its local learning dataset, while a master server mainta…
Whole-Graph Representation Learning For the Classification of Signed Networks
Noé Cecillon, Vincent Labatut, Richard Dufour +1
Graphs are ubiquitous for modeling complex systems involving structured data and relationships. Consequently, graph representation learning, which aims to automatically learn low-d…
An Analysis of Linear Complexity Attention Substitutes with BEST-RQ
Ryan Whetten, Titouan Parcollet, Adel Moumen +2
Self-Supervised Learning (SSL) has proven to be effective in various domains, including speech processing. However, SSL is computationally and memory expensive. This is in part due…
Explaining a probabilistic prediction on the simplex with Shapley compositions
Paul-Gauthier Noé, Miquel Perelló-Nieto, Jean-François Bonastre +1
Originating in game theory, Shapley values are widely used for explaining a machine learning model's prediction by quantifying the contribution of each feature's value to the predi…