{"type":"ScholarlyArticle","title":"A Ladder of Causal Distances","authors":[{"name":"Maxime Peyrard","slug":"maxime-peyrard","given":"Maxime","family":"Peyrard","affiliation":""},{"name":"Robert West","slug":"robert-west","given":"Robert","family":"West","affiliation":""}],"abstract":"Causal discovery, the task of automatically constructing a causal model from data, is of major significance across the sciences.\r\nEvaluating the performance of causal discovery algorithms should ideally involve comparing the inferred models to ground-truth models available for benchmark datasets, which in turn requires a notion of distance between causal models.\r\nWhile such distances have been proposed previously, they are limited by focusing on graphical properties of the causal models being compared.\r\nHere, we overcome this limitation by defining distances derived from the causal distributions induced by the models, rather than exclusively from their graphical structure.\r\nPearl and Mackenzie [2018] have arranged the properties of causal models in a hierarchy called the ``ladder of causation'' spanning three rungs: observational, interventional, and counterfactual.\r\nFollowing this organization, we introduce a hierarchy of three distances, one for each rung of the ladder.\r\nOur definitions are intuitively appealing as well as efficient to compute approximately.\r\nWe put our causal distances to use by benchmarking standard causal discovery systems on both synthetic and real-world datasets for which ground-truth causal models are available.","doi":"10.24963/ijcai.2021/277","url":"https://ijcai.org/proceedings/2021/277","pdf":"https://ijcai.org/proceedings/2021/0277.pdf","markdown":"https://ijcai.org/proceedings/2021/277.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/277","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":277,"pages":{"first":2012,"last":2018},"keywords":["Uncertainty in AI: Bayesian Networks","Knowledge Representation and Reasoning: Action, Change and Causality"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}