The whole machinery of Machine Learning techniques relies on the fact that a decision rule can be learnt by looking at a set of labeled examples called the learning sample. Then this decision is applied to the whole population which is assumed to follow the same underlying distribution. In many cases, learning samples may present biases either due to the presence of a real but unwanted bias in the observations (societal bias for instance) or due to the way the data are processed (multiple sensors, parallelized inference, evolution in the distribution or unbalanced sample…) Hence the goal of this research is twofold : to detect, analyze and remove such biases, which is called fair leaning ; then understand the way the biases are created and provide more robust, certifiable and explainable methods to tackle the distributional effects in machine learning including transfert learning, consensus learning, theoretical bounds and robustness.

Applications to Societal issues of Artificial Intelligence but also to Industrial Applications

Keywords : machine Learning, Optimal Transport, Wasserstein Barycenter, Transfert Learning, Adversarial Learning, Robustness

Research Program for Fairness

*Organization of CIMI Fairness Seminar for AOC members (2017-2018)

• Theoretical properties of fair learning
  
  • Using optimal transport Theory (with E. del Barrio (U. Valladolid), P. Gordaliza (U. Valladolid-Phd), F. Gamboa). OT Theory is a strong theme in Mathematical Institute of Valladolid
    • Ensuring Fairness with OT for classification
    • Fairness in regression (work in progress)
  • Fairness in clustering and allocation problems
    • Fair clustering (with E. del Barrio and H. Inouzhe (U. Valladolid-Phd))
    • Fairness in predictive police (private report for French Ministry of National Security with C. Castets-Renard (UT1), P. Besse (INSA), L. Perrusel(UT1))
  •  Tests and Wasserstein distance (with P. Besse, E. del Barrio, P. Gordaliza)
    • CLT for Wasserstein distance,
    • CLT and application to Fairness
    • Confidence Interval for Disparate Impact Estimation
  • Error bounds for Fair bandits algorithms (work in progress with G. Fortin-Stolz (Orsay))

• New feasible algorithms to promote fairness
  • with adversarial network (work in progress with E. Pauwels (IRIT), M. Serrurier (IRIT))
  • with Optimal Transport Cost penalty (work in progress with L. Risser (CNRS), N. Couellan (ENAC))
• Fairness and Legal Issues ( paper with C. Castets-Renard (UT1), P. Besse (INSA), A. Garivier (ENS Lyon))
• Explainable IA : paper with F. Bachoc (IMT) F. Gamboa and L. Risser. We promote global explainability by stressing the variables of a black-box model in order to analyze their particular effect in the decision rule, toolbox coming soon.
  
  • The project is detailled here
• Consensus and transfert Learning using OT (work in progress with H. Inouzhe, E. del Barrio, C. Matrán (U. Valladolid) A. Mayo-Iscar (U. Valladolid)

 

This Research won CNRS innovation prize  (project Ethik-IA) and was also selected by Toulouse’s University Valorization team. The purpose is to provide a Python’s toolbox (coming soon).

Popular Science :

• video in french,
• Le Monde’s newspaper (02/2019),
• 20 minutes newspaper (11/2018).

Github link for codes and tutorial (here and here)