Interpretable Regional Descriptors: Hyperbox-Based Local Explanations

MCML Authors

Susanne Dandl

Dr.

* Former Member

→ Group Bernd Bischl
 Statistical Learning and Data Science

Giuseppe Casalicchio

Dr.

→ Group Bernd Bischl
 Statistical Learning and Data Science

Bernd Bischl

Prof. Dr.

Director

Statistical Learning and Data Science

Ludwig Bothmann

Dr.

→ Group Bernd Bischl
 Statistical Learning and Data Science

Abstract

This work introduces interpretable regional descriptors, or IRDs, for local, model-agnostic interpretations. IRDs are hyperboxes that describe how an observation’s feature values can be changed without affecting its prediction. They justify a prediction by providing a set of “even if” arguments (semi-factual explanations), and they indicate which features affect a prediction and whether pointwise biases or implausibilities exist. A concrete use case shows that this is valuable for both machine learning modelers and persons subject to a decision. We formalize the search for IRDs as an optimization problem and introduce a unifying framework for computing IRDs that covers desiderata, initialization techniques, and a post-processing method. We show how existing hyperbox methods can be adapted to fit into this unified framework. A benchmark study compares the methods based on several quality measures and identifies two strategies to improve IRDs.

inproceedings DCB+23

---

ECML-PKDD 2023

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Turin, Italy, Sep 18-22, 2023.

---

Authors

S. Dandl • G. Casalicchio • B. Bischl • L. Bothmann

---

Links

DOI

---

Research Area

 A1 | Statistical Foundations & Explainability