Conditional Generative Models for Counterfactual Explanations
arXiv:2101.10123
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.
12 pages
References in corpus (11)
- Auto-Encoding Variational Bayes
- Conditional Generative Adversarial Nets
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Categorical Reparameterization with Gumbel-Softmax
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
- Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
- Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
- Adversarial Audio Synthesis
- A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
- Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's Decision