{"type":"ScholarlyArticle","title":"Updates on the Complexity of SHAP Scores","authors":[{"name":"Xuanxiang Huang","slug":"xuanxiang-huang","given":"Xuanxiang","family":"Huang","affiliation":""},{"name":"Joao Marques-Silva","slug":"joao-marques-silva","given":"Joao","family":"Marques-Silva","affiliation":""}],"abstract":"SHAP scores represent one of the most widely used methods of explainability by feature attribution, as illustrated by the explainable AI tool SHAP.\r\nA number of recent works studied the computational complexity of the exact computation of SHAP scores, covering a comprehensive range of families of classifiers.\r\nThis paper refines some of the existing complexity claims, including families of classifiers for which the computation of SHAP scores is computationally hard and those for which there exist polynomial-time algorithms.","doi":"10.24963/ijcai.2024/45","url":"https://ijcai.org/proceedings/2024/45","pdf":"https://ijcai.org/proceedings/2024/0045.pdf","markdown":"https://ijcai.org/proceedings/2024/45.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/45","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"AI Ethics, Trust, Fairness","track":"Main Track","number":45,"pages":{"first":403,"last":412},"keywords":["AI Ethics, Trust, Fairness: ETF: Explainability and interpretability","AI Ethics, Trust, Fairness: ETF: Trustworthy AI","Knowledge Representation and Reasoning: KRR: Computational complexity of reasoning","Machine Learning: ML: Explainable/Interpretable machine learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}