Exact Integrated Gradients for tree ensembles, including XGBoost, LightGBM, Random Forests, and Gradient Boosting. Computes fast, exact feature attributions for tree models without numerical gradients, numerical integration, Monte Carlo sampling, or path approximations.
Provides a unified approach to Integrated Gradients: a common API for many models, include tree-based models; and common baseline semantics with prediction-neutral baseline distributions as the default.
Analytic input gradients and Jacobians for supported fitted scikit-learn models, including linear models, kernel SVMs, MLPs, and preprocessing pipelines.
