Interpretable Companions for Black-Box Models

By Danqing Pan, Tong Wang, Satoshi Hara. 2020

10 citations recorded by the source corpus.

We present an interpretable companion model for any pre-trained black-box classifiers. The idea is that for any input, a user can decide to either receive a prediction from the black-box model, with high accuracy but no explanations, or employ a companion rule to obtain an interpretable prediction with slightly lower accuracy. The companion model is trained from data and the predictions of the black-box model, with the objective combining area under the transparency--accuracy curve and model complexity. Our model provides flexible choices for practitioners who face the dilemma of choosing between always using interpretable models and always using black-box models for a predictive task, so users can, for any given input, take a step back to resort to an interpretable prediction if they find the predictive performance satisfying, or stick to the black-box model if the rules are unsatisfying. To show the value of companion models, we design a human evaluation on more than a hundred people to investigate the tolerable accuracy loss to gain interpretability for humans.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tong Wang
2. Jingyi Yang
3. Yunyi Li
4. Boxiang Wang

Citations in the corpus

• Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning (2021, methodology): “Model Hybrids The idea of utilizing an interpretable model and a black-box model jointly to make a prediction is similar to recent works of hybrid models (Wang, 2019; Pan et al., 2020).”