# On Logic-Based Explainability with Partially Specified Inputs

arXiv: https://arxiv.org/abs/2306.15803 · HTML: https://mlsanity.com/paper/2306.15803/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 63 references that are in the map.
- First posted on arXiv 27 Jun 2023.

## Builds on (most cited first, 23 of 23)

- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Abduction-Based Explanations for Machine Learning Models](https://mlsanity.com/paper/1811.10656/) (2018)
- [A Symbolic Approach to Explaining Bayesian Network Classifiers](https://mlsanity.com/paper/1805.03364/) (2018)
- [On The Reasons Behind Decisions](https://mlsanity.com/paper/2002.09284/) (2020)
- [Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning](https://mlsanity.com/paper/1912.08881/) (2019)
- [Model Interpretability through the Lens of Computational Complexity](https://mlsanity.com/paper/2010.12265/) (2020)
- [What's a good imputation to predict with missing values?](https://mlsanity.com/paper/2106.00311/) (2021)
- [On Explaining Random Forests with SAT](https://mlsanity.com/paper/2105.10278/) (2021)
- [On Guaranteed Optimal Robust Explanations for NLP Models](https://mlsanity.com/paper/2105.03640/) (2021)
- [On Tackling Explanation Redundancy in Decision Trees](https://mlsanity.com/paper/2205.09971/) (2022)
- [On the Computational Intelligibility of Boolean Classifiers](https://mlsanity.com/paper/2104.06172/) (2021)
- [On Computing Probabilistic Explanations for Decision Trees](https://mlsanity.com/paper/2207.12213/) (2022)
- [Foundations of Symbolic Languages for Model Interpretability](https://mlsanity.com/paper/2110.02376/) (2021)
- [ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanations](https://mlsanity.com/paper/2206.11900/) (2022)
- [Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Values](https://mlsanity.com/paper/2109.10431/) (2021)
- [Feature Necessity & Relevancy in ML Classifier Explanations](https://mlsanity.com/paper/2210.15675/) (2022)
- [On Computing Probabilistic Abductive Explanations](https://mlsanity.com/paper/2212.05990/) (2022)
- [On Quantifying Literals in Boolean Logic and Its Applications to Explainable AI](https://mlsanity.com/paper/2108.09876/) (2021)
- [What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Features](https://mlsanity.com/paper/1903.01620/) (2019)
- [Handling Missing Data in Decision Trees: A Probabilistic Approach](https://mlsanity.com/paper/2006.16341/) (2020)
- [Explaining Chemical Toxicity using Missing Features](https://mlsanity.com/paper/2009.12199/) (2020)
- [Algorithmic Recourse with Missing Values](https://mlsanity.com/paper/2304.14606/) (2023)

## Abstract (arXiv)

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.