Keywords: [ ReScience - MLRC 2021 ] [ Journal Track ]
This work aims to reproduce Lang et al.'s StylEx which proposes a novel approach to explain how a classifier makes its decision. They claim that StylEx creates a post-hoc counterfactual explanation whose principal attributes correspond to properties that are intuitive to humans. The paper boasts a large range of real-world practicality. However, StylEx proves difficult to reproduce due to its time complexity and holes in the information provided. This paper tries to fill in these holes by: i) re-implementation of StylEx in a different framework, ii) creating a low resource training benchmark.