A revised version of our paper “Fairness Explainability using Optimal Transport with Applications in Image Classification” is now online, with more discussion about conterfactuals
Ensuring trust and accountability in Artificial Intelligence systems demands explainability of its outcomes. Despite significant progress in Explainable AI, human biases still taint a substantial portion of its training data, raising concerns about unfairness or discriminatory tendencies. Current approaches in the field of Algorithmic Fairness focus on mitigating such biases in the outcomes of a model, but few attempts have been made to try to explain why a model is biased. To bridge this gap between the two fields, we propose a comprehensive approach that uses optimal transport theory to uncover the causes of discrimination in Machine Learning applications, with a particular emphasis on image classification. We leverage Wasserstein barycenters to achieve fair predictions and introduce an extension to pinpoint bias-associated regions. This allows us to derive a cohesive system which uses the enforced fairness to measure each features influence on the bias.Taking advantage of this interplay of enforcing and explaining fairness, our method hold significant implications for the development of trustworthy and unbiased AI systems, fostering transparency, accountability, and fairness in critical decision-making scenarios across diverse domains.
For those who wish to reproduce the techniques proposed in our paper, Optimal Transport for Counterfactual Estimation: A Method for Causal Inference, Ewen Gallic has put online some nice pages, with the application mentioned in the paper (both univariate and bivariate, including confidence intervals with bootstrap), as well as simpler examples, which I use in the slides, to present the method
I will present this work at the Bachelier Seminar, in Paris, at the end of the week. Slides are online here.
Many problems ask a question that can be formulated as a causal question: “what would have happened if…?” For example, “would the person have had surgery if he or she had been Black?” To address this kind of questions, calculating an average treatment effect (ATE) is often uninformative, because one would like to know how much impact a variable (such as skin color) has on a specific individual, characterized by certain covariates. Trying to calculate a conditional ATE (CATE) seems more appropriate. In causal inference, the propensity score approach assumes that the treatment is influenced by x, a collection of covariates. Here, we will have the dual view: doing an intervention, or changing the treatment (even just hypothetically, in a thought experiment, for example by asking what would have happened if a person had been Black) can have an impact on the values of x. We will see here that optimal transport allows us to change certain characteristics that are influenced by the variable we are trying to quantify the effect of. We propose here a mutatis mutandis version of the CATE, which will be done simply in dimension one by saying that the CATE must be computed relative to a level of probability, associated to the proportion of x (a single covariate) in the control population, and by looking for the equivalent quantile in the test population. In higher dimension, it will be necessary to go through transport, and an application will be proposed on the impact of some variables on the probability of having an unnatural birth (the fact that the mother smokes, or that the mother is Black).
This week, the Sixth International Econometric Conference of Vietnaml (ECONVN2023) is taking place at Ho Chi Minh City, Vietnam. I will present some recent work, with Emmanuel Flachaire and Ewen Gallic on causal inference with optimal transport. The slides are now online (an updated version of the paper will be on ArXiv soon).