Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning
By Tong Wang, Jingyi Yang, Yunyi Li, Boxiang Wang. 2021
5 citations recorded by the source corpus.
We propose Partially Interpretable Estimators (PIE) which attribute a prediction to individual features via an interpretable model, while a (possibly) small part of the PIE prediction is attributed to the interaction of features via a black-box model, with the goal to boost the predictive performance while maintaining interpretability. As such, the interpretable model captures the main contributions of features, and the black-box model attempts to complement the interpretable piece by capturing the"nuances"of feature interactions as a refinement. We design an iterative training algorithm to jointly train the two types of models. Experimental results show that PIE is highly competitive to black-box models while outperforming interpretable baselines. In addition, the understandability of PIE is comparable to simple linear models as validated via a human evaluation.
Subfields: Safety, Robustness & Interpretability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Safety, Robustness & Interpretability
- Lesia Semenova
- Zhi Chen
- Chudi Zhong
- Haiyang Huang
- Cynthia Rudin
- Octavio Loyola-González
- Tong Wang
- S. Lo Piano
Citations in the corpus
- Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, methodology): “One such framework for matching is the Almost Matching Exactly framework (Wang et al., 2021), which learns the important variables using a training set, and prioritizes matching on those important variables.”