Induction of Non-Monotonic Logic Programs to Explain Boosted Tree Models Using LIME

Authors

  • Farhad Shakerin University of Texas at Dallas
  • Gopal Gupta University of Texas at Dallas

DOI:

https://doi.org/10.1609/aaai.v33i01.33013052

Abstract

We present a heuristic based algorithm to induce 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 nonmonotonic 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.

Downloads

Published

2019-07-17

How to Cite

Shakerin, F., & Gupta, G. (2019). Induction of Non-Monotonic Logic Programs to Explain Boosted Tree Models Using LIME. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 3052-3059. https://doi.org/10.1609/aaai.v33i01.33013052

Issue

Section

AAAI Technical Track: Knowledge Representation and Reasoning