Attribution-Scores in Data Management and Explainable Machine Learning
This work addresses the need for explainability in data management and ML, but it appears incremental as it builds on existing concepts like database repairs and responsibility scores.
The paper tackles the problem of explaining query answers in databases and classification outcomes in machine learning by using responsibility scores based on actual causality, and it explores efficient computation methods like Shap-score.
We describe recent research on the use of actual causality in the definition of responsibility scores as explanations for query answers in databases, and for outcomes from classification models in machine learning. In the case of databases, useful connections with database repairs are illustrated and exploited. Repairs are also used to give a quantitative measure of the consistency of a database. For classification models, the responsibility score is properly extended and illustrated. The efficient computation of Shap-score is also analyzed and discussed. The emphasis is placed on work done by the author and collaborators.