Open the Black Box Data-Driven Explanation of Black Box Decision Systems
arXiv:1806.09936
Abstract
Black box systems for automated decision making, often based on machine learning over (big) data, map a user's features into a class or a score without exposing the reasons why. This is problematic not only for lack of transparency, but also for possible biases hidden in the algorithms, due to human prejudices and collection artifacts hidden in the training data, which may lead to unfair or wrong decisions. We introduce the local-to-global framework for black box explanation, a novel approach with promising early results, which paves the road for a wide spectrum of future developments along three dimensions: (i) the language for expressing explanations in terms of highly expressive logic-based rules, with a statistical and causal interpretation; (ii) the inference of local explanations aimed at revealing the logic of the decision adopted for a specific instance by querying and auditing the black box in the vicinity of the target instance; (iii), the bottom-up generalization of the many local explanations into simple global ones, with algorithms that optimize the quality and comprehensibility of explanations.
References in corpus (7)
- Fairness Testing: Testing Software for Discrimination
- Local Rule-Based Explanations of Black Box Decision Systems
- Algorithmic Methods to Infer the Evolutionary Trajectories in Cancer Progression
- Exposing the Probabilistic Causal Structure of Discrimination
- Making Tree Ensembles Interpretable
- The Temporal Logic of Causal Structures
- Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable
Cited by in corpus (6)
- Auditing of AI: Legal, Ethical and Technical Approaches
- How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review
- Ethics-Based Auditing of Automated Decision-Making Systems: Intervention Points and Policy Implications
- Responsible AI by Design in Practice
- Semantic XAI for contextualized demand forecasting explanations
- An Active Approach for Model Interpretation