Function Trees: Transparent Machine Learning
This provides a method for improving transparency and interpretability in machine learning, particularly for understanding model predictions and system dynamics, though it appears incremental as it builds on existing function representation concepts.
The paper tackles the problem of interpreting complex machine learning models by representing multivariate functions as trees of simpler functions, which uncovers joint influences of input subsets and enables rapid computation and visualization of main and interaction effects up to four variables.
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.