Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning

2021/05/06 by Wang, Tong, Yang, Jingyi, Li, Yunyi +1
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2105.02410

Abstract

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.

Related

• Regularizing Black-box Models for Improved Interpretability (HILL 2019\n Version)
• Hybrid Predictive Model: When an Interpretable Model Collaborates with a Black-box Model
• Interpretable Companions for Black-Box Models
• Lifting Interpretability-Performance Trade-off via Automated Feature Engineering
• A Double Penalty Model for Interpretability