Local Rule-Based Explanations of Black Box Decision Systems
Preprint
Abstract
The recent years have witnessed the rise of accurate but obscure decision systems which hide the logic of their internal decision processes to the users. The lack of explanations for the decisions of black box systems is a key ethical issue, and a limitation to the adoption of machine learning components in socially sensitive and safety-critical contexts. %Therefore, we need explanations that reveals the reasons why a predictor takes a certain decision. In this paper we focus on the problem of black box outcome explanation, i.e., explaining the reasons of the decision taken on a specific instance. We propose LORE, an agnostic method able to provide interpretable and faithful explanations. LORE first leans a local interpretable predictor on a synthetic neighborhood generated by a genetic algorithm. Then it derives from the logic of the local interpretable predictor a meaningful explanation consisting of: a decision rule, which explains the reasons of the decision; and a set of counterfactual rules, suggesting the changes in the instance's features that lead to a different outcome. Wide experiments show that LORE outperforms existing methods and baselines both in the quality of explanations and in the accuracy in mimicking the black box.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Why a Right to Explanation of Automated Decision-Making Does Not Exist in the General Data Protection RegulationInternational Data Privacy Law, 2017
- A peek into the black box: exploring classifiers by randomizationData Mining and Knowledge Discovery, 2014
- Genetic algorithms in feature and instance selectionKnowledge-Based Systems, 2013
- A survey on instance selection for active learningKnowledge and Information Systems, 2012
- Reverse Engineering the Neural Networks for Rule Extraction in Classification ProblemsNeural Processing Letters, 2011
- A review of instance selection methodsArtificial Intelligence Review, 2010
- Distance functions for categorical and mixed variablesPattern Recognition Letters, 2008
- Stratification for scaling up evolutionary prototype selectionPattern Recognition Letters, 2005
- Extracting decision trees from trained neural networksPattern Recognition, 1999
- Survey and critique of techniques for extracting rules from trained artificial neural networksKnowledge-Based Systems, 1995