Towards Knowledge-driven Distillation and Explanation of Black-box Models.

In Roberto Confalonieri, Guendalina Righetti, Pietro Galliani, Nicolas Toquard, Oliver Kutz & Daniele Porello (eds.), Proceedings of the Workshop on Data meets Applied Ontologies in Explainable {AI} {(DAO-XAI} 2021) part of Bratislava Knowledge September {(BAKS} 2021), Bratislava, Slovakia, September 18th to 19th, 2021. CEUR 2998 (2021)
  Copy   BIBTEX

Abstract

We introduce and discuss a knowledge-driven distillation approach to explaining black-box models by means of two kinds of interpretable models. The first is perceptron (or threshold) connectives, which enrich knowledge representation languages such as Description Logics with linear operators that serve as a bridge between statistical learning and logical reasoning. The second is Trepan Reloaded, an ap- proach that builds post-hoc explanations of black-box classifiers in the form of decision trees enhanced by domain knowledge. Our aim is, firstly, to target a model-agnostic distillation approach exemplified with these two frameworks, secondly, to study how these two frameworks interact on a theoretical level, and, thirdly, to investigate use-cases in ML and AI in a comparative manner. Specifically, we envision that user-studies will help determine human understandability of explanations generated using these two frameworks.

Author Profiles

Analytics

Added to PP
2022-04-03

Downloads
323 (#52,178)

6 months
95 (#46,349)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?