# Integrating Prior Knowledge in Post-hoc Explanations

arXiv: https://arxiv.org/abs/2204.11634 · HTML: https://mlsanity.com/paper/2204.11634/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 14 of 14)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Actionable Recourse in Linear Classification](https://mlsanity.com/paper/1809.06514/) (2018)
- [FACE: Feasible and Actionable Counterfactual Explanations](https://mlsanity.com/paper/1909.09369/) (2019)
- [A Survey on the Explainability of Supervised Machine Learning](https://mlsanity.com/paper/2011.07876/) (2020)
- [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019)
- [Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers](https://mlsanity.com/paper/1912.03277/) (2019)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Generalized Inverse Classification](https://mlsanity.com/paper/1610.01675/) (2016)
- [bLIMEy: Surrogate Prediction Explanations Beyond LIME](https://mlsanity.com/paper/1910.13016/) (2019)
- [Local Interpretable Model-agnostic Explanations of Bayesian Predictive Models via Kullback-Leibler Projections](https://mlsanity.com/paper/1810.02678/) (2018)

## Built on by (most cited first, 2 of 2)

- [Achieving Diversity in Counterfactual Explanations: a Review and Discussion](https://mlsanity.com/paper/2305.05840/) (2023)
- [Why do explanations fail? A typology and discussion on failures in XAI](https://mlsanity.com/paper/2405.13474/) (2024)

## Abstract (arXiv)

In the field of eXplainable Artificial Intelligence (XAI), post-hoc interpretability methods aim at explaining to a user the predictions of a trained decision model. Integrating prior knowledge into such interpretability methods aims at improving the explanation understandability and allowing for personalised explanations adapted to each user. In this paper, we propose to define a cost function that explicitly integrates prior knowledge into the interpretability objectives: we present a general framework for the optimization problem of post-hoc interpretability methods, and show that user knowledge can thus be integrated to any method by adding a compatibility term in the cost function. We instantiate the proposed formalization in the case of counterfactual explanations and propose a new interpretability method called Knowledge Integration in Counterfactual Explanation (KICE) to optimize it. The paper performs an experimental study on several benchmark data sets to characterize the counterfactual instances generated by KICE, as compared to reference methods.