Function Trees: Transparent Machine Learning

TL;DR

This paper introduces Function Trees, a method to represent complex multivariate functions as interpretable trees, revealing global structure and interactions among input variables for better understanding and explanation of machine learning models.

Contribution

The paper presents a novel approach to decompose multivariate functions into tree structures, enabling visualization and analysis of variable influences and interactions.

Findings

Function Trees effectively visualize interactions involving up to four variables.

The method allows rapid identification of main and interaction effects.

It enhances interpretability of complex machine learning models.

Abstract

The output of a machine learning algorithm can usually be represented by one or more multivariate functions of its input variables. Knowing the global properties of such functions can help in understanding the system that produced the data as well as interpreting and explaining corresponding model predictions. A method is presented for representing a general multivariate function as a tree of simpler functions. This tree exposes the global internal structure of the function by uncovering and describing the combined joint influences of subsets of its input variables. Given the inputs and corresponding function values, a function tree is constructed that can be used to rapidly identify and compute all of the function's main and interaction effects up to high order. Interaction effects involving up to four variables are graphically visualized.