Score-Based Explanations in Data Management and Machine Learning: An Answer-Set Programming Approach to Counterfactual Analysis
This work addresses the need for interpretable explanations in data management and machine learning, but it appears incremental as it builds on the author's prior research.
The paper tackles the problem of generating score-based explanations for query answers in databases and classification outcomes in machine learning, using declarative approaches based on answer-set programming and counterfactual reasoning to specify and compute these scores, with several examples demonstrating the flexibility of the methods.
We describe some recent approaches to score-based explanations for query answers in databases and outcomes from classification models in machine learning. The focus is on work done by the author and collaborators. Special emphasis is placed on declarative approaches based on answer-set programming to the use of counterfactual reasoning for score specification and computation. Several examples that illustrate the flexibility of these methods are shown.