VCNet: A self-explaining model for realistic counterfactual generation
This addresses the problem of interpretability in ML for users needing actionable explanations, though it is incremental as it builds on existing counterfactual methods.
The paper tackles the challenge of generating realistic counterfactual explanations for machine learning decisions by proposing VCNet, a model that jointly trains a predictor and counterfactual generator, resulting in competitive performance with state-of-the-art methods on tabular datasets.
Counterfactual explanation is a common class of methods to make local explanations of machine learning decisions. For a given instance, these methods aim to find the smallest modification of feature values that changes the predicted decision made by a machine learning model. One of the challenges of counterfactual explanation is the efficient generation of realistic counterfactuals. To address this challenge, we propose VCNet-Variational Counter Net-a model architecture that combines a predictor and a counterfactual generator that are jointly trained, for regression or classification tasks. VCNet is able to both generate predictions, and to generate counterfactual explanations without having to solve another minimisation problem. Our contribution is the generation of counterfactuals that are close to the distribution of the predicted class. This is done by learning a variational autoencoder conditionally to the output of the predictor in a join-training fashion. We present an empirical evaluation on tabular datasets and across several interpretability metrics. The results are competitive with the state-of-the-art method.