Hierarchical Knowledge Extraction from Opaque Machine Learning Predictors

Advances in Artificial Intelligence
Lecture Notes in Computer Science (AIxIA 2024) 15450
Springer, Cham
2025

Adopting opaque machine learning predictors, which achieve
very high predictive performance, often necessitates incorporating sym-
bolic knowledge-extraction techniques. These techniques aim to explain
the opaque predictions, thus making them applicable in high-stakes sce-
narios. The development of symbolic knowledge-extraction procedures is
evolving alongside the dynamic machine learning landscape. However,
there are recurring drawbacks that tend to be overlooked or addressed in
a suboptimum way. Common examples include the non-exhaustiveness
of the global explanations generated for a black-box predictor or the
unwanted discretisation introduced in the prediction of continuous vari-
ables. To tackle these challenges, in this work, we introduce the HEx
algorithm, its formalisation and its properties. This algorithm aims to
obtain a symbolic, hierarchical representation of the knowledge acquired
by opaque machine learning classifiers and regressors, always ensuring
knowledge exhaustiveness and avoiding any output discretisation. Ex-
periments demonstrating the superior capabilities of HEx compared to
state-of-the-art competitors in terms of predictive performance, com-
pleteness, and human readability are presented.

keywordsExplainable artificial intelligence· Symbolic knowledge ex- traction· PSyKE
origin event
funding project
wrenchAEQUITAS — Assessment and Engineering of eQuitable, Unbiased, Impartial and Trustworthy Ai Systems (01/11/2022–31/10/2025)
wrenchFAIR-PE01-SP08 — Future AI Research – Partenariato Esteso sull'Intelligenza Artificiale – Spoke 8 “Pervasive AI” (01/01/2023–31/12/2025)