Neural Causal Abstractions

arXiv:2401.02602v2 Announce Type: replace
Abstract: The abilities of humans to understand the world in terms of cause and effect relationships, as well as to compress information into abstract concepts, are two hallmark features of human intelligence. These two topics have been studied in tandem in the literature under the rubric of causal abstractions theory. In practice, it remains an open problem how to best leverage abstraction theory in real-world causal inference tasks, where the true mechanisms are unknown and only …

abstract abstractions arxiv cause and effect concepts cs.ai cs.lg features hallmark human human intelligence humans information intelligence literature practice relationships terms theory topics type world