Induction of Non-Monotonic Logic Programs to Explain Boosted Tree Models Using LIME
This work addresses the interpretability of complex machine learning models for practitioners, though it is incremental as it builds on existing LIME and ILP methods.
The paper tackles the problem of explaining boosted tree models by inducing non-monotonic logic programs, using LIME for local feature selection and proposing the LIME-FOLD algorithm for global explanations. The result shows significant improvement in classification metrics and a dramatic reduction in the number of induced rules compared to the ALEPH system.
We present a heuristic based algorithm to induce \textit{nonmonotonic} logic programs that will explain the behavior of XGBoost trained classifiers. We use the technique based on the LIME approach to locally select the most important features contributing to the classification decision. Then, in order to explain the model's global behavior, we propose the LIME-FOLD algorithm ---a heuristic-based inductive logic programming (ILP) algorithm capable of learning non-monotonic logic programs---that we apply to a transformed dataset produced by LIME. Our proposed approach is agnostic to the choice of the ILP algorithm. Our experiments with UCI standard benchmarks suggest a significant improvement in terms of classification evaluation metrics. Meanwhile, the number of induced rules dramatically decreases compared to ALEPH, a state-of-the-art ILP system.