The Shapley Value in Database Management

Abstract

Attribution scores can be applied in data management to quantify the contribution of individual items to conclusions from the data, as part of the explanation of what led to these conclusions. In Artificial Intelligence, Machine Learning, and Data Management, some of the common scores are deployments of the Shapley value, a formula for profit sharing in cooperative game theory. Since its invention in the 1950s, the Shapley value has been used for contribution measurement in many fields, from economics to law, with its latest researched applications in modern machine learning. Recent studies investigated the application of the Shapley value to database management. This article gives an overview of recent results on the computational complexity of the Shapley value for measuring the contribution of tuples to query answers and to the extent of inconsistency with respect to integrity constraints. More specifically, the article highlights lower and upper bounds on the complexity of calculating the Shapley value, either exactly or approximately, as well as solutions for realizing the calculation in practice.

arXiv comment12 pages, including references. This is the authors version of the corresponding SIGMOD Record article

References in corpus (7)

• A Unified Approach to Interpreting Model Predictions
• A Survey on the Explainability of Supervised Machine Learning
• The Shapley Value of Inconsistency Measures for Functional Dependencies
• Quantifying Causal Effects on Query Answering in Databases
• On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results
• Exact and Approximate Counting of Database Repairs
• The Complexity of the Shapley Value for Regular Path Queries

Cited by in corpus (3)

• A Comprehensive Study of Shapley Value in Data Analytics
• SHARQ: Explainability Framework for Association Rules on Relational Data
• Causality-Based Scores Alignment in Explainable Data Management