Causality-Based Scores Alignment in Explainable Data Management
This work addresses the need for consistent explanations in data management, but it is incremental as it builds on existing scores without introducing new methods.
The paper tackled the problem of aligning different attribution scores for database query answering by investigating whether they produce compatible rankings of tuples, and found that the presence of exogenous tuples is a key factor, with a syntactic dichotomy result showing some score pairs are always aligned while others are not.
Different attribution scores have been proposed to quantify the relevance of database tuples for query answering in databases; e.g. Causal Responsibility, the Shapley Value, the Banzhaf Power-Index, and the Causal Effect. They have been analyzed in isolation. This work is a first investigation of score alignment depending on the query and the database; i.e. on whether they induce compatible rankings of tuples. We concentrate mostly on causality-based scores; and provide a syntactic dichotomy result for queries: on one side, pairs of scores are always aligned, on the other, they are not always aligned. It turns out that the presence of exogenous tuples makes a crucial difference in this regard.