Conditional Generative Models for Counterfactual Explanations

by   Arnaud Van Looveren, et al.

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.



There are no comments yet.


page 1

page 4

page 9

page 10


DA-DGCEx: Ensuring Validity of Deep Guided Counterfactual Explanations With Distribution-Aware Autoencoder Loss

Deep Learning has become a very valuable tool in different fields, and n...

Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning

Counterfactual instances are a powerful tool to obtain valuable insights...

Counterfactual Control for Free from Generative Models

We introduce a method by which a generative model learning the joint dis...

Generative Counterfactual Introspection for Explainable Deep Learning

In this work, we propose an introspection technique for deep neural netw...

What went wrong and when? Instance-wise Feature Importance for Time-series Models

Multivariate time series models are poised to be used for decision suppo...

Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

Counterfactual explanations (CEs) are a practical tool for demonstrating...

On Counterfactual Explanations under Predictive Multiplicity

Counterfactual explanations are usually obtained by identifying the smal...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.