EU Horizon 2020
Horizon 2020
HomeNewsResearch ThemesPeopleKey Prior PublicationsPublications
[QSJ+23] Francesco Quinzan, Ashkan Soleymani, Patrik Jaillet, Cristian R. Rojas, Stefan Bauer. DRCFS: Doubly Robust Causal Feature Selection. In ICML2023 Fortieth International Conference on Machine Learning. To appear. 2023. [pdf] [bib]
Downloads:  pdf pdf (1.49 MB)  bib bib
Abstract. Knowing the features of a complex system that are highly relevant to a particular target variable is of fundamental interest in many areas of science. Existing approaches are often limited to linear settings, sometimes lack guarantees, and in most cases, do not scale to the problem at hand, in particular to images. We propose DRCFS, a doubly robust feature selection method for identifying the causal features even in nonlinear and high dimensional settings. We provide theoretical guarantees, illustrate necessary conditions for our assumptions, and perform extensive experiments across a wide range of simulated and semisynthetic datasets. DRCFS significantly outperforms existing state-of-the-art methods, selecting robust features even in challenging highly nonlinear and high-dimensional problems.