Speaker: Annabelle Redelmeier (NR)

Time: Friday, December 3, 2021, 10-11

Location: NR (Alfa/omega) or Click here to join meeting (Microsoft Teams)

Title: MCCE: Monte Carlo sampling of realistic counterfactual explanations

Annabelle Redelmeier's talk will be based on a paper that is available on arXiv.

Summary: In this paper we introduce MCCE: Monte Carlo sampling of realistic Counterfactual Explanations, a model-based method that generates counterfactual explanations by generating a synthetic data set using conditional infrence trees. Unlike algorithmic based counterfactual methods that have to solve complex optimization problems or other model based methods that model the data distribution using heavy machine learning models, MCCE is made up of only two light-weight steps generation and post-processing, is straight forward for the end user to understand and implement, handles any type of predictive model, f(), and type of feature, x, takes into account actionability constraints when generating the counterfactual explanations, and generates as many counterfactual explanations as needed. In this paper we introduce MCCE and give a comprehensive list of evaluation metrics that can be used to compare counterfactual explanations. We also compare MCCE with a range of state-of-the-art counterfactual methods and a new baseline method on benchmark data sets.