Interpreting Deep Forest through Feature Contribution and MDI Feature Importance

TL;DR

This paper introduces methods to interpret deep forest models by estimating feature contributions and global feature importance, addressing the challenge of interpretability in multi-layer random forest architectures.

Contribution

It proposes novel calculation methods for feature contribution and MDI importance tailored for deep forest, enabling interpretability beyond the first layer.

Findings

Effective in simulated data

Validated on real-world data

Enhances interpretability of deep forest models

Abstract

Deep forest is a non-differentiable deep model which has achieved impressive empirical success across a wide variety of applications, especially on categorical/symbolic or mixed modeling tasks. Many of the application fields prefer explainable models, such as random forests with feature contributions that can provide local explanation for each prediction, and Mean Decrease Impurity (MDI) that can provide global feature importance. However, deep forest, as a cascade of random forests, possesses interpretability only at the first layer. From the second layer on, many of the tree splits occur on the new features generated by the previous layer, which makes existing explanatory tools for random forests inapplicable. To disclose the impact of the original features in the deep layers, we design a calculation method with an estimation step followed by a calibration step for each layer, and propose our feature contribution and MDI feature importance calculation tools for deep forest. Experimental results on both simulated data and real world data verify the effectiveness of our methods.