English

Metafeatures-based Rule-Extraction for Classifiers on Behavioral and Textual Data

Artificial Intelligence 2021-07-01 v3 Machine Learning

Abstract

Machine learning models on behavioral and textual data can result in highly accurate prediction models, but are often very difficult to interpret. Rule-extraction techniques have been proposed to combine the desired predictive accuracy of complex "black-box" models with global explainability. However, rule-extraction in the context of high-dimensional, sparse data, where many features are relevant to the predictions, can be challenging, as replacing the black-box model by many rules leaves the user again with an incomprehensible explanation. To address this problem, we develop and test a rule-extraction methodology based on higher-level, less-sparse metafeatures. A key finding of our analysis is that metafeatures-based explanations are better at mimicking the behavior of the black-box prediction model, as measured by the fidelity of explanations.

Keywords

Cite

@article{arxiv.2003.04792,
  title  = {Metafeatures-based Rule-Extraction for Classifiers on Behavioral and Textual Data},
  author = {Yanou Ramon and David Martens and Theodoros Evgeniou and Stiene Praet},
  journal= {arXiv preprint arXiv:2003.04792},
  year   = {2021}
}

Comments

31 pages, 13 figures

R2 v1 2026-06-23T14:10:20.144Z