DeepAI AI Chat
Log In Sign Up

Consistent Counterfactuals for Deep Models

by   Emily Black, et al.

Counterfactual examples are one of the most commonly-cited methods for explaining the predictions of machine learning models in key areas such as finance and medical diagnosis. Counterfactuals are often discussed under the assumption that the model on which they will be used is static, but in deployment models may be periodically retrained or fine-tuned. This paper studies the consistency of model prediction on counterfactual examples in deep networks under small changes to initial training conditions, such as weight initialization and leave-one-out variations in data, as often occurs during model deployment. We demonstrate experimentally that counterfactual examples for deep models are often inconsistent across such small changes, and that increasing the cost of the counterfactual, a stability-enhancing mitigation suggested by prior work in the context of simpler models, is not a reliable heuristic in deep networks. Rather, our analysis shows that a model's local Lipschitz continuity around the counterfactual is key to its consistency across related models. To this end, we propose Stable Neighbor Search as a way to generate more consistent counterfactual explanations, and illustrate the effectiveness of this approach on several benchmark datasets.


Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers

Explaining the output of a complex machine learning (ML) model often req...

On Quantitative Evaluations of Counterfactuals

As counterfactual examples become increasingly popular for explaining de...

Gradient-based Counterfactual Explanations using Tractable Probabilistic Models

Counterfactual examples are an appealing class of post-hoc explanations ...

ECINN: Efficient Counterfactuals from Invertible Neural Networks

Counterfactual examples identify how inputs can be altered to change the...

Two-step counterfactual generation for OOD examples

Two fundamental requirements for the deployment of machine learning mode...

CREATED: Generating Viable Counterfactual Sequences for Predictive Process Analytics

Predictive process analytics focuses on predicting future states, such a...