Practical Causal Reasoning as a Means for Ethical ML

In this talk I will give an overview of the role of causality in ethical machine learning, and in particular, in fair and explainable ML. In particular, I will first detail how to use causal reasoning to study fairness and interpretability problems in algorithmic decision making, stressing the main limitations that we encounter when aiming to address these problems in practice. Then, I will introduce the audience to causal generative models, a novel class of deep generative models that do not only accurately fit observational data but can also provide accurate estimates to interventional and counterfactual queries. I will focus this part of the talk on our recent paper DeCaFlow, a deconfounding causal generative model (CGM). DeCaFlow can provably identify all causal queries with a valid adjustment set or sufficiently informative proxy variables. Remarkably, for the first time to our knowledge, we show that a confounded counterfactual query is identifiable, and thus solvable by DeCaFlow, as long as its interventional counterpart is as well.