Global Explanations with Decision Rules: a Co-learning Approach

Research output: Contribution in Book/Catalog/Report/Conference proceedingConference contribution

84 Downloads (Pure)

Abstract

Black-box machine learning models can be extremely accurate. Yet, in critical applications such as in healthcare or justice, if models cannot be explained, domain experts will be reluctant to use them. A common way to explain a black-box model is to approximate it by a simpler model such as a decision tree. In this paper, we propose a co-learning framework to learn decision rules as explanations of black-box models through knowledge distillation and simultaneously constrain the black-box model by these explanations; all of this in a differentiable manner. To do so, we introduce the soft truncated Gaussian mixture analysis (STruGMA), a probabilistic model which encapsulates hyper-rectangle decision rules. With STruGMA, global explanations can be extracted by any rule learner such as decision lists, sets or trees. We provide evidences through experiments that our framework can globally explain differentiable black-box models such as neural networks. In particular, the explanation fidelity is increased, while the accuracy of the models is marginally impacted.
Original languageEnglish
Title of host publicationProceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence
EditorsCassio de Campos, Marloes H. Maathuis
PublisherMLResearch Press
Pages589-599
Number of pages11
Publication statusPublished - 27 Jul 2021

Publication series

NameProceedings of Machine Learning Research
PublisherMLResearchPress
Volume161
ISSN (Electronic)2640-3498

Keywords

  • Constraints
  • Explainability
  • Deciision Rules

Fingerprint

Dive into the research topics of 'Global Explanations with Decision Rules: a Co-learning Approach'. Together they form a unique fingerprint.

Cite this