Publication

Conditional Generative Models for Counterfactual Explanations

Publication

Conditional Generative Models for Counterfactual Explanations

Abstract

Counterfactual instances offer human-interpretable insight into the local behaviour of machine learning models. We propose a general framework to generate sparse, in-distribution counterfactual model explanations which match a desired target prediction with a conditional generative model, allowing batches of counterfactual instances to be generated with a single forward pass. The method is flexible with respect to the type of generative model used as well as the task of the underlying predictive model. This allows straightforward application of the framework to different modalities such as images, time series or tabular data as well as generative model paradigms such as GANs or autoencoders and predictive tasks like classification or regression. We illustrate the effectiveness of our method on image (CelebA), time series (ECG) and mixed-type tabular (Adult Census) data.

Date of publication:
January 1, 1970

Cookies!

Yep, it’s another exciting cookie notice. We use cookies on this website to do some cool stuff such as the choose tech or exec button. Nothing sinister! You can read our privacy policies and terms of use etc by clicking here.