Author:
Arenas Marcelo,Barceló Pablo,Bertossi Leopoldo,Monet Mikaël
Abstract
Scores based on Shapley values are widely used for providing explanations to classification results over machine learning models. A prime example of this is the influential SHAP-score, a version of the Shapley value that can help explain the result of a learned model on a specific entity by assigning a score to every feature. While in general computing Shapley values is a computationally intractable problem, it has recently been claimed that the SHAP-score can be computed in polynomial time over the class of decision trees. In this paper, we provide a proof of a stronger result over Boolean models: the SHAP-score can be computed in polynomial time over deterministic and decomposable Boolean circuits. Such circuits, also known as tractable Boolean circuits, generalize a wide range of Boolean circuits and binary decision diagrams classes, including binary decision trees, Ordered Binary Decision Diagrams (OBDDs) and Free Binary Decision Diagrams (FBDDs). We also establish the computational limits of the notion of SHAP-score by observing that, under a mild condition, computing it over a class of Boolean models is always polynomially as hard as the model counting problem for that class. This implies that both determinism and decomposability are essential properties for the circuits that we consider, as removing one or the other renders the problem of computing the SHAP-score intractable (namely, #P-hard).
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
13 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Explainability Is
Not
a Game;Communications of the ACM;2024-07
2. Banzhaf Values for Facts in Query Answering;Proceedings of the ACM on Management of Data;2024-05-29
3. Knowledge compilation;Annals of Mathematics and Artificial Intelligence;2024-05-17
4. Expected Shapley-Like Scores of Boolean functions: Complexity and Applications to Probabilistic Databases;Proceedings of the ACM on Management of Data;2024-05-10
5. From Shapley Value to Model Counting and Back;Proceedings of the ACM on Management of Data;2024-05-10