Interpreting Deep Forest through Feature Contribution and MDI Feature Importance
This work addresses the need for explainable AI in fields using deep forest models, though it is incremental as it extends existing interpretability tools to a specific model architecture.
The paper tackles the problem of interpreting deep forest models, which lack explainability beyond the first layer, by proposing new methods to calculate feature contributions and MDI feature importance for deep layers, with experimental validation on simulated and real-world data showing effectiveness.
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.