Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285340650> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4285340650 abstract "Underrepresentation and misrepresentation of protected groups in the training data is a significant source of bias for Machine Learning (ML) algorithms, resulting in decreased confidence and trustworthiness of the generated ML models. Such bias can be mitigated by incorporating both objective as well as subjective (through human users) measures of bias, and compensating for them by means of a suitable selection algorithm over subgroups of training data. In this paper, we propose a methodology of integrating bias detection and mitigation strategies through interactive visualization of machine learning models in selected protected spaces. In this approach, a (partially generated) ML model performance is visualized and evaluated by a human user or a community of human users in terms of potential presence of bias using both objective and subjective criteria. Guided by such human feedback, the ML algorithm can implement a variety of remedial sampling strategies to mitigate the bias using an iterative human-in-the-loop approach. We also provide experimental results with a benchmark ML dataset to demonstrate that such an interactive ML approach holds considerable promise in detecting and mitigating bias in ML models." @default.
- W4285340650 created "2022-07-14" @default.
- W4285340650 creator A5004575115 @default.
- W4285340650 creator A5058530487 @default.
- W4285340650 creator A5072472948 @default.
- W4285340650 creator A5080102032 @default.
- W4285340650 date "2021-10-29" @default.
- W4285340650 modified "2023-10-14" @default.
- W4285340650 title "An Interactive Approach to Bias Mitigation in Machine Learning" @default.
- W4285340650 cites W1501005121 @default.
- W4285340650 cites W1901365844 @default.
- W4285340650 cites W1981119726 @default.
- W4285340650 cites W2012457675 @default.
- W4285340650 cites W2014352947 @default.
- W4285340650 cites W2045649112 @default.
- W4285340650 cites W2116984840 @default.
- W4285340650 cites W2147427185 @default.
- W4285340650 cites W2223235514 @default.
- W4285340650 cites W2343061342 @default.
- W4285340650 cites W2394669110 @default.
- W4285340650 cites W2512274390 @default.
- W4285340650 cites W2512304460 @default.
- W4285340650 cites W2584805976 @default.
- W4285340650 cites W2587299461 @default.
- W4285340650 cites W2906804290 @default.
- W4285340650 cites W2908730746 @default.
- W4285340650 cites W2913994026 @default.
- W4285340650 cites W2948130259 @default.
- W4285340650 cites W2962977061 @default.
- W4285340650 cites W2964023221 @default.
- W4285340650 cites W2964060106 @default.
- W4285340650 cites W4247397307 @default.
- W4285340650 cites W4289258088 @default.
- W4285340650 cites W4289751798 @default.
- W4285340650 doi "https://doi.org/10.1109/iccicc53683.2021.9811333" @default.
- W4285340650 hasPublicationYear "2021" @default.
- W4285340650 type Work @default.
- W4285340650 citedByCount "1" @default.
- W4285340650 countsByYear W42853406502023 @default.
- W4285340650 crossrefType "proceedings-article" @default.
- W4285340650 hasAuthorship W4285340650A5004575115 @default.
- W4285340650 hasAuthorship W4285340650A5058530487 @default.
- W4285340650 hasAuthorship W4285340650A5072472948 @default.
- W4285340650 hasAuthorship W4285340650A5080102032 @default.
- W4285340650 hasConcept C105795698 @default.
- W4285340650 hasConcept C119857082 @default.
- W4285340650 hasConcept C129848803 @default.
- W4285340650 hasConcept C13280743 @default.
- W4285340650 hasConcept C154945302 @default.
- W4285340650 hasConcept C17744445 @default.
- W4285340650 hasConcept C185798385 @default.
- W4285340650 hasConcept C199539241 @default.
- W4285340650 hasConcept C205649164 @default.
- W4285340650 hasConcept C2779602731 @default.
- W4285340650 hasConcept C33923547 @default.
- W4285340650 hasConcept C40423286 @default.
- W4285340650 hasConcept C41008148 @default.
- W4285340650 hasConcept C75917345 @default.
- W4285340650 hasConceptScore W4285340650C105795698 @default.
- W4285340650 hasConceptScore W4285340650C119857082 @default.
- W4285340650 hasConceptScore W4285340650C129848803 @default.
- W4285340650 hasConceptScore W4285340650C13280743 @default.
- W4285340650 hasConceptScore W4285340650C154945302 @default.
- W4285340650 hasConceptScore W4285340650C17744445 @default.
- W4285340650 hasConceptScore W4285340650C185798385 @default.
- W4285340650 hasConceptScore W4285340650C199539241 @default.
- W4285340650 hasConceptScore W4285340650C205649164 @default.
- W4285340650 hasConceptScore W4285340650C2779602731 @default.
- W4285340650 hasConceptScore W4285340650C33923547 @default.
- W4285340650 hasConceptScore W4285340650C40423286 @default.
- W4285340650 hasConceptScore W4285340650C41008148 @default.
- W4285340650 hasConceptScore W4285340650C75917345 @default.
- W4285340650 hasLocation W42853406501 @default.
- W4285340650 hasOpenAccess W4285340650 @default.
- W4285340650 hasPrimaryLocation W42853406501 @default.
- W4285340650 hasRelatedWork W112744582 @default.
- W4285340650 hasRelatedWork W1485630101 @default.
- W4285340650 hasRelatedWork W2498017833 @default.
- W4285340650 hasRelatedWork W2961085424 @default.
- W4285340650 hasRelatedWork W3046775127 @default.
- W4285340650 hasRelatedWork W4285260836 @default.
- W4285340650 hasRelatedWork W4286629047 @default.
- W4285340650 hasRelatedWork W4306321456 @default.
- W4285340650 hasRelatedWork W4306674287 @default.
- W4285340650 hasRelatedWork W4224009465 @default.
- W4285340650 isParatext "false" @default.
- W4285340650 isRetracted "false" @default.
- W4285340650 workType "article" @default.