Timezone: »

 
Poster
Model Agnostic Supervised Local Explanations
Gregory Plumb · Denali Molitor · Ameet Talwalkar

Tue Dec 04 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #129
in Tue Poster Session B »

Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based, local, and global explanations. One of the main challenges in interpretability is designing explanation systems that can capture aspects of each of these explanation types, in order to develop a more thorough understanding of the model. We address this challenge in a novel model called MAPLE that uses local linear modeling techniques along with a dual interpretation of random forests (both as a supervised neighborhood approach and as a feature selection method). MAPLE has two fundamental advantages over existing interpretability systems. First, while it is effective as a black-box explanation system, MAPLE itself is a highly accurate predictive model that provides faithful self explanations, and thus sidesteps the typical accuracy-interpretability trade-off. Specifically, we demonstrate, on several UCI datasets, that MAPLE is at least as accurate as random forests and that it produces more faithful local explanations than LIME, a popular interpretability system. Second, MAPLE provides both example-based and local explanations and can detect global patterns, which allows it to diagnose limitations in its local explanations.

Keywords: Classification · Regression · Fairness, Accountability, and Transparency · Boosting and Ensemble Methods
[ Paper] 

Author Information

Gregory Plumb (CMU)
Denali Molitor (University of California, Los Angeles)
Ameet Talwalkar (CMU)

More from the Same Authors