Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317465472> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4317465472 abstract "Algorithm fairness in the application of artificial intelligence (AI) is essential for a better society. As the foundational axiom of social mechanisms, fairness consists of multiple facets. Although the machine learning (ML) community has focused on intersectionality as a matter of statistical parity, especially in discrimination issues, an emerging body of literature addresses another facet -- monotonicity. Based on domain expertise, monotonicity plays a vital role in numerous fairness-related areas, where violations could misguide human decisions and lead to disastrous consequences. In this paper, we first systematically evaluate the significance of applying monotonic neural additive models (MNAMs), which use a fairness-aware ML algorithm to enforce both individual and pairwise monotonicity principles, for the fairness of AI ethics and society. We have found, through a hybrid method of theoretical reasoning, simulation, and extensive empirical analysis, that considering monotonicity axioms is essential in all areas of fairness, including criminology, education, health care, and finance. Our research contributes to the interdisciplinary research at the interface of AI ethics, explainable AI (XAI), and human-computer interactions (HCIs). By evidencing the catastrophic consequences if monotonicity is not met, we address the significance of monotonicity requirements in AI applications. Furthermore, we demonstrate that MNAMs are an effective fairness-aware ML approach by imposing monotonicity restrictions integrating human intelligence." @default.
- W4317465472 created "2023-01-20" @default.
- W4317465472 creator A5064457396 @default.
- W4317465472 creator A5080633583 @default.
- W4317465472 date "2023-01-17" @default.
- W4317465472 modified "2023-10-01" @default.
- W4317465472 title "Monotonicity for AI ethics and society: An empirical study of the monotonic neural additive model in criminology, education, health care, and finance" @default.
- W4317465472 doi "https://doi.org/10.48550/arxiv.2301.07060" @default.
- W4317465472 hasPublicationYear "2023" @default.
- W4317465472 type Work @default.
- W4317465472 citedByCount "0" @default.
- W4317465472 crossrefType "posted-content" @default.
- W4317465472 hasAuthorship W4317465472A5064457396 @default.
- W4317465472 hasAuthorship W4317465472A5080633583 @default.
- W4317465472 hasBestOaLocation W43174654721 @default.
- W4317465472 hasConcept C105795698 @default.
- W4317465472 hasConcept C119857082 @default.
- W4317465472 hasConcept C120936955 @default.
- W4317465472 hasConcept C134306372 @default.
- W4317465472 hasConcept C144237770 @default.
- W4317465472 hasConcept C154945302 @default.
- W4317465472 hasConcept C15744967 @default.
- W4317465472 hasConcept C162324750 @default.
- W4317465472 hasConcept C167729594 @default.
- W4317465472 hasConcept C184898388 @default.
- W4317465472 hasConcept C194959371 @default.
- W4317465472 hasConcept C2524010 @default.
- W4317465472 hasConcept C33923547 @default.
- W4317465472 hasConcept C41008148 @default.
- W4317465472 hasConcept C45555294 @default.
- W4317465472 hasConcept C50644808 @default.
- W4317465472 hasConcept C539667460 @default.
- W4317465472 hasConcept C72169020 @default.
- W4317465472 hasConceptScore W4317465472C105795698 @default.
- W4317465472 hasConceptScore W4317465472C119857082 @default.
- W4317465472 hasConceptScore W4317465472C120936955 @default.
- W4317465472 hasConceptScore W4317465472C134306372 @default.
- W4317465472 hasConceptScore W4317465472C144237770 @default.
- W4317465472 hasConceptScore W4317465472C154945302 @default.
- W4317465472 hasConceptScore W4317465472C15744967 @default.
- W4317465472 hasConceptScore W4317465472C162324750 @default.
- W4317465472 hasConceptScore W4317465472C167729594 @default.
- W4317465472 hasConceptScore W4317465472C184898388 @default.
- W4317465472 hasConceptScore W4317465472C194959371 @default.
- W4317465472 hasConceptScore W4317465472C2524010 @default.
- W4317465472 hasConceptScore W4317465472C33923547 @default.
- W4317465472 hasConceptScore W4317465472C41008148 @default.
- W4317465472 hasConceptScore W4317465472C45555294 @default.
- W4317465472 hasConceptScore W4317465472C50644808 @default.
- W4317465472 hasConceptScore W4317465472C539667460 @default.
- W4317465472 hasConceptScore W4317465472C72169020 @default.
- W4317465472 hasLocation W43174654721 @default.
- W4317465472 hasOpenAccess W4317465472 @default.
- W4317465472 hasPrimaryLocation W43174654721 @default.
- W4317465472 hasRelatedWork W1883420430 @default.
- W4317465472 hasRelatedWork W1981397021 @default.
- W4317465472 hasRelatedWork W2032883556 @default.
- W4317465472 hasRelatedWork W2070757250 @default.
- W4317465472 hasRelatedWork W2071811385 @default.
- W4317465472 hasRelatedWork W2560284039 @default.
- W4317465472 hasRelatedWork W2610036410 @default.
- W4317465472 hasRelatedWork W2739339900 @default.
- W4317465472 hasRelatedWork W2763181606 @default.
- W4317465472 hasRelatedWork W3168491208 @default.
- W4317465472 isParatext "false" @default.
- W4317465472 isRetracted "false" @default.
- W4317465472 workType "article" @default.