On Logic-Based Explainability with Partially Specified Inputs

TL;DR

This paper explores how to generate logic-based explanations for machine learning predictions when some input data is missing or partially specified, showing that existing algorithms can be adapted without increasing complexity.

Contribution

It demonstrates that algorithms for logic-based explanations can be generalized to handle partially specified inputs without added computational complexity.

Findings

Algorithms are adaptable to partial inputs

Complexity remains unchanged with partial data

Applied to real datasets for new explainability use cases

Abstract

In the practical deployment of machine learning (ML) models, missing data represents a recurring challenge. Missing data is often addressed when training ML models. But missing data also needs to be addressed when deciding predictions and when explaining those predictions. Missing data represents an opportunity to partially specify the inputs of the prediction to be explained. This paper studies the computation of logic-based explanations in the presence of partially specified inputs. The paper shows that most of the algorithms proposed in recent years for computing logic-based explanations can be generalized for computing explanations given the partially specified inputs. One related result is that the complexity of computing logic-based explanations remains unchanged. A similar result is proved in the case of logic-based explainability subject to input constraints. Furthermore, the proposed solution for computing explanations given partially specified inputs is applied to classifiers obtained from well-known public datasets, thereby illustrating a number of novel explainability use cases.