Log In Sign Up

Computing Abductive Explanations for Boosted Trees

by   Gilles Audemard, et al.

Boosted trees is a dominant ML model, exhibiting high accuracy. However, boosted trees are hardly intelligible, and this is a problem whenever they are used in safety-critical applications. Indeed, in such a context, rigorous explanations of the predictions made are expected. Recent work have shown how subset-minimal abductive explanations can be derived for boosted trees, using automated reasoning techniques. However, the generation of such well-founded explanations is intractable in the general case. To improve the scalability of their generation, we introduce the notion of tree-specific explanation for a boosted tree. We show that tree-specific explanations are abductive explanations that can be computed in polynomial time. We also explain how to derive a subset-minimal abductive explanation from a tree-specific explanation. Experiments on various datasets show the computational benefits of leveraging tree-specific explanations for deriving subset-minimal abductive explanations.


page 1

page 2

page 3

page 4


Provably Precise, Succinct and Efficient Explanations for Decision Trees

Decision trees (DTs) embody interpretable classifiers. DTs have been adv...

Towards Formal Approximated Minimal Explanations of Neural Networks

With the rapid growth of machine learning, deep neural networks (DNNs) a...

Evaluating Tree Explanation Methods for Anomaly Reasoning: A Case Study of SHAP TreeExplainer and TreeInterpreter

Understanding predictions made by Machine Learning models is critical in...

Improved Feature Importance Computations for Tree Models: Shapley vs. Banzhaf

Shapley values are one of the main tools used to explain predictions of ...

Extracting Optimal Explanations for Ensemble Trees via Logical Reasoning

Ensemble trees are a popular machine learning model which often yields h...

Crown-CAM: Reliable Visual Explanations for Tree Crown Detection in Aerial Images

Visual explanation of "black-box" models has enabled researchers and exp...

Defining Explanation in Probabilistic Systems

As probabilistic systems gain popularity and are coming into wider use, ...