%0 Conference Proceedings
%9 ACTI : Communications avec actes dans un congrès international
%A Ruiz Cuevas, M.V.
%A Sokolovska, N.
%A Wuillemin, P.H.
%A Zucker, Jean-Daniel
%T Detecting low-complexity confounders from data
%D 2018
%L fdi:010073292
%G ENG
%K INTELLIGENCE ARTIFICIELLE ; INFORMATIQUE SCIENTIFIQUE ; ANALYSE MULTIVARIABLE ; MEDECINE ; BIOLOGIE
%N 80
%P 3
%U https://www.documentation.ird.fr/hor/fdi:010073292
%> https://horizon.documentation.ird.fr/exl-doc/pleins_textes/divers18-08/010073292.pdf
%W Horizon (IRD)
%X Statistical dependencies between two variables X and Y indicate that either X causes Y , or Y causes X, or there exists a latent variable Z which influences X and Y. In biology and medicine, an important problem is to find genetic or environmental unobserved causes of phenotypic difference between individuals. In this contribution, we introduce a novel approach to identify unobserved confounders in data. The proposed method is based on the state-of-the-art 3off2 causal network reconstruction algorithm, and on an evidence for a direct causal relation represented by purity of con-ditionals. The proposed method is implemented in Python, and it will be publicly available shortly. We discuss the results obtained on a real biomedical dataset.
%B ICML : International Conference on Machine Learning ; CausalML : Machine Learning for Causal Inference, Counterfactual Prediction, and Autonomous Action
%8 2018/07/10-15
%$ 122INTAR