Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386794927> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4386794927 abstract "Artificial intelligence models and methods commonly lack causal interpretability. Despite the advancements in interpretable machine learning (IML) methods, they frequently assign importance to features which lack causal influence on the outcome variable. Selecting causally relevant features among those identified as relevant by these methods, or even before model training, would offer a solution. Feature selection methods utilizing information theoretical quantities have been successful in identifying statistically relevant features. However, the information theoretical quantities they are based on do not incorporate causality, rendering them unsuitable for such scenarios. To address this challenge, this article proposes information theoretical quantities that incorporate the causal structure of the system, which can be used to evaluate causal importance of features for some given outcome variable. Specifically, we introduce causal versions of entropy and mutual information, termed causal entropy and causal information gain, which are designed to assess how much control a feature provides over the outcome variable. These newly defined quantities capture changes in the entropy of a variable resulting from interventions on other variables. Fundamental results connecting these quantities to the existence of causal effects are derived. The use of causal information gain in feature selection is demonstrated, highlighting its superiority over standard mutual information in revealing which features provide control over a chosen outcome variable. Our investigation paves the way for the development of methods with improved interpretability in domains involving causation." @default.
- W4386794927 created "2023-09-16" @default.
- W4386794927 creator A5028760842 @default.
- W4386794927 creator A5065990141 @default.
- W4386794927 creator A5076111740 @default.
- W4386794927 date "2023-09-14" @default.
- W4386794927 modified "2023-10-01" @default.
- W4386794927 title "Causal Entropy and Information Gain for Measuring Causal Control" @default.
- W4386794927 doi "https://doi.org/10.48550/arxiv.2309.07703" @default.
- W4386794927 hasPublicationYear "2023" @default.
- W4386794927 type Work @default.
- W4386794927 citedByCount "0" @default.
- W4386794927 crossrefType "posted-content" @default.
- W4386794927 hasAuthorship W4386794927A5028760842 @default.
- W4386794927 hasAuthorship W4386794927A5065990141 @default.
- W4386794927 hasAuthorship W4386794927A5076111740 @default.
- W4386794927 hasBestOaLocation W43867949271 @default.
- W4386794927 hasConcept C105795698 @default.
- W4386794927 hasConcept C106301342 @default.
- W4386794927 hasConcept C11671645 @default.
- W4386794927 hasConcept C119857082 @default.
- W4386794927 hasConcept C121332964 @default.
- W4386794927 hasConcept C124101348 @default.
- W4386794927 hasConcept C134306372 @default.
- W4386794927 hasConcept C144237770 @default.
- W4386794927 hasConcept C148220186 @default.
- W4386794927 hasConcept C148483581 @default.
- W4386794927 hasConcept C152139883 @default.
- W4386794927 hasConcept C154945302 @default.
- W4386794927 hasConcept C163504300 @default.
- W4386794927 hasConcept C166151441 @default.
- W4386794927 hasConcept C17744445 @default.
- W4386794927 hasConcept C182365436 @default.
- W4386794927 hasConcept C199539241 @default.
- W4386794927 hasConcept C2781067378 @default.
- W4386794927 hasConcept C33923547 @default.
- W4386794927 hasConcept C41008148 @default.
- W4386794927 hasConcept C62520636 @default.
- W4386794927 hasConcept C64357122 @default.
- W4386794927 hasConceptScore W4386794927C105795698 @default.
- W4386794927 hasConceptScore W4386794927C106301342 @default.
- W4386794927 hasConceptScore W4386794927C11671645 @default.
- W4386794927 hasConceptScore W4386794927C119857082 @default.
- W4386794927 hasConceptScore W4386794927C121332964 @default.
- W4386794927 hasConceptScore W4386794927C124101348 @default.
- W4386794927 hasConceptScore W4386794927C134306372 @default.
- W4386794927 hasConceptScore W4386794927C144237770 @default.
- W4386794927 hasConceptScore W4386794927C148220186 @default.
- W4386794927 hasConceptScore W4386794927C148483581 @default.
- W4386794927 hasConceptScore W4386794927C152139883 @default.
- W4386794927 hasConceptScore W4386794927C154945302 @default.
- W4386794927 hasConceptScore W4386794927C163504300 @default.
- W4386794927 hasConceptScore W4386794927C166151441 @default.
- W4386794927 hasConceptScore W4386794927C17744445 @default.
- W4386794927 hasConceptScore W4386794927C182365436 @default.
- W4386794927 hasConceptScore W4386794927C199539241 @default.
- W4386794927 hasConceptScore W4386794927C2781067378 @default.
- W4386794927 hasConceptScore W4386794927C33923547 @default.
- W4386794927 hasConceptScore W4386794927C41008148 @default.
- W4386794927 hasConceptScore W4386794927C62520636 @default.
- W4386794927 hasConceptScore W4386794927C64357122 @default.
- W4386794927 hasLocation W43867949271 @default.
- W4386794927 hasOpenAccess W4386794927 @default.
- W4386794927 hasPrimaryLocation W43867949271 @default.
- W4386794927 hasRelatedWork W1767411471 @default.
- W4386794927 hasRelatedWork W2154360918 @default.
- W4386794927 hasRelatedWork W216496316 @default.
- W4386794927 hasRelatedWork W2315864143 @default.
- W4386794927 hasRelatedWork W2494150180 @default.
- W4386794927 hasRelatedWork W2903145669 @default.
- W4386794927 hasRelatedWork W2997391570 @default.
- W4386794927 hasRelatedWork W3163334550 @default.
- W4386794927 hasRelatedWork W4225915909 @default.
- W4386794927 hasRelatedWork W4287823982 @default.
- W4386794927 isParatext "false" @default.
- W4386794927 isRetracted "false" @default.
- W4386794927 workType "article" @default.