Distilling Interpretable Models into Human-Readable Code

TL;DR

This paper introduces a method to convert complex models into simple, human-readable code by distilling their knowledge into piecewise-linear functions, enhancing interpretability and manual editability.

Contribution

It proposes a novel distillation approach that approximates models with concise, interpretable piecewise-linear functions, enabling easier review and manual modification.

Findings

Effective across classification, regression, and ranking tasks.

Produces accurate, concise, and human-readable models.

Demonstrates broad applicability with four datasets.

Abstract

The goal of model distillation is to faithfully transfer teacher model knowledge to a model which is faster, more generalizable, more interpretable, or possesses other desirable characteristics. Human-readability is an important and desirable standard for machine-learned model interpretability. Readable models are transparent and can be reviewed, manipulated, and deployed like traditional source code. As a result, such models can be improved outside the context of machine learning and manually edited if desired. Given that directly training such models is difficult, we propose to train interpretable models using conventional methods, and then distill them into concise, human-readable code. The proposed distillation methodology approximates a model's univariate numerical functions with piecewise-linear curves in a localized manner. The resulting curve model representations are accurate, concise, human-readable, and well-regularized by construction. We describe a piecewise-linear curve-fitting algorithm that produces high-quality results efficiently and reliably across a broad range of use cases. We demonstrate the effectiveness of the overall distillation technique and our curve-fitting algorithm using four datasets across the tasks of classification, regression, and ranking.