Search Results for author: Laurent Risser

Found 14 papers, 7 papers with code

Debiasing Machine Learning Models by Using Weakly Supervised Learning

no code implementations23 Feb 2024 Renan D. B. Brotto, Jean-Michel Loubes, Laurent Risser, Jean-Pierre Florens, Kenji Nose-Filho, João M. T. Romano

In our work, we then propose a bias mitigation strategy for continuous sensitive variables, based on the notion of endogeneity which comes from the field of econometrics.

Econometrics Weakly-supervised Learning

TaCo: Targeted Concept Removal in Output Embeddings for NLP via Information Theory and Explainability

1 code implementation11 Dec 2023 Fanny Jourdan, Louis Béthune, Agustin Picard, Laurent Risser, Nicholas Asher

In evaluation, we show that the proposed post-hoc approach significantly reduces gender-related associations in NLP models while preserving the overall performance and functionality of the models.


Toulouse Hyperspectral Data Set: a benchmark data set to assess semi-supervised spectral representation learning and pixel-wise classification techniques

2 code implementations15 Nov 2023 Romain Thoreau, Laurent Risser, Véronique Achard, Béatrice Berthelot, Xavier Briottet

While the spectral dimension of hyperspectral images is highly informative of the chemical composition of the land surface, the use of state-of-the-art machine learning algorithms to map the land cover has been dramatically limited by the availability of training data.

Representation Learning Self-Supervised Learning

Are fairness metric scores enough to assess discrimination biases in machine learning?

no code implementations8 Jun 2023 Fanny Jourdan, Laurent Risser, Jean-Michel Loubes, Nicholas Asher

This paper presents novel experiments shedding light on the shortcomings of current metrics for assessing biases of gender discrimination made by machine learning algorithms on textual data.


COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks

1 code implementation11 May 2023 Fanny Jourdan, Agustin Picard, Thomas Fel, Laurent Risser, Jean Michel Loubes, Nicholas Asher

COCKATIEL is a novel, post-hoc, concept-based, model-agnostic XAI technique that generates meaningful explanations from the last layer of a neural net model trained on an NLP classification task by using Non-Negative Matrix Factorization (NMF) to discover the concepts the model leverages to make predictions and by exploiting a Sensitivity Analysis to estimate accurately the importance of each of these concepts for the model.

Explainable Artificial Intelligence (XAI) Sentiment Analysis

How optimal transport can tackle gender biases in multi-class neural-network classifiers for job recommendations?

no code implementations27 Feb 2023 Fanny Jourdan, Titon Tshiongo Kaninku, Nicholas Asher, Jean-Michel Loubes, Laurent Risser

To anticipate the certification of recommendation systems using textual data, we then used it on the Bios dataset, for which the learning task consists in predicting the occupation of female and male individuals, based on their LinkedIn biography.

Multi-class Classification Recommendation Systems

A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis

no code implementations10 Oct 2022 Laurent Risser, Agustin Picard, Lucas Hervier, Jean-Michel Loubes

Contrarily to societal applications where a set of proxy variables can be provided by the common sense or by regulations to draw the attention on potential risks, industrial and safety-critical applications are most of the times sailing blind.

Common Sense Reasoning Fairness

Transport-based Counterfactual Models

1 code implementation30 Aug 2021 Lucas de Lara, Alberto González-Sanz, Nicholas Asher, Laurent Risser, Jean-Michel Loubes

We address the problem of designing realistic and feasible counterfactuals in the absence of a causal model.

Causal Inference counterfactual +1

Tackling Algorithmic Bias in Neural-Network Classifiers using Wasserstein-2 Regularization

no code implementations15 Aug 2019 Laurent Risser, Alberto Gonzalez Sanz, Quentin Vincenot, Jean-Michel Loubes

We then introduce in this paper a new method to temper the algorithmic bias in Neural-Network based classifiers.

Explaining Machine Learning Models using Entropic Variable Projection

2 code implementations18 Oct 2018 François Bachoc, Fabrice Gamboa, Max Halford, Jean-Michel Loubes, Laurent Risser

In order to emphasize the impact of each input variable, this formalism uses an information theory framework that quantifies the influence of all input-output observations based on entropic projections.

BIG-bench Machine Learning

COREclust: a new package for a robust and scalable analysis of complex data

no code implementations25 May 2018 Camille Champion, Anne-Claire Brunet, Jean-Michel Loubes, Laurent Risser

In this paper, we present a new R package COREclust dedicated to the detection of representative variables in high dimensional spaces with a potentially limited number of observations.

Clustering Graph Clustering

Anisotropic Diffusion in ITK

no code implementations3 Mar 2015 Jean-Marie Mirebeau, Jérôme Fehrenbach, Laurent Risser, Shaza Tobji

Anisotropic Non-Linear Diffusion is a powerful image processing technique, which allows to simultaneously remove the noise and enhance sharp features in two or three dimensional images.

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