Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations

TL;DR

This paper introduces DiVE, a method that generates diverse, non-trivial counterfactual explanations for machine learning models, improving interpretability by uncovering multiple valuable insights beyond trivial attribute changes.

Contribution

DiVE learns disentangled perturbations with diversity constraints to produce meaningful, non-trivial counterfactual explanations, addressing limitations of existing methods.

Findings

DiVE outperforms previous methods in generating valuable explanations.

The approach effectively prevents trivial counterfactuals.

Experiments on CelebA and Synbols validate the method's effectiveness.

Abstract

Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems. In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction, providing details about the model's decision-making. Current methods tend to generate trivial counterfactuals about a model's decisions, as they often suggest to exaggerate or remove the presence of the attribute being classified. For the machine learning practitioner, these types of counterfactuals offer little value, since they provide no new information about undesired model or data biases. In this work, we identify the problem of trivial counterfactual generation and we propose DiVE to alleviate it. DiVE learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss to uncover multiple valuable explanations about the model's prediction. Further, we introduce a mechanism to prevent the model from producing trivial explanations. Experiments on CelebA and Synbols demonstrate that our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods. Code is available at https://github.com/ElementAI/beyond-trivial-explanations.