FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159045897> ?p ?o ?g. }

• W3159045897 abstract "Though machine learning models are achieving great success, ex-tensive studies have exposed their disadvantage of inheriting latent discrimination and societal bias from the training data, which hinders their adoption on high-state applications. Thus, many efforts have been taken for developing fair machine learning models. Most of them require that sensitive attributes are available during training to learn fair models. However, in many real-world applications, it is usually infeasible to obtain the sensitive attribute due to privacy or legal issues, which challenges existing fair classifiers. Though the sensitive attribute of each data sample is unknown, we observe that there are usually some non-sensitive features in the training data that are highly correlated with sensitive attributes, which can be used to alleviate the bias. Therefore, in this paper, we study a novel problem of exploring features that are highly correlated with sensitive attributes for learning fair and accurate classifier without sensitive attributes. We theoretically show that by minimizing the correlation between these related features and model prediction, we can learn a fair classifier. Based on this motivation, we propose a novel framework which simultaneously uses these related features for accurate prediction and regularizing the model to be fair. In addition, the model can dynamically adjust the importance weight of each related feature to balance the contribution of the feature on model classification and fairness. Experimental results on real-world datasets demonstrate the effectiveness of the proposed model for learning fair models with high classification accuracy." @default.
• W3159045897 created "2021-05-10" @default.
• W3159045897 creator A5011048500 @default.
• W3159045897 creator A5053042660 @default.
• W3159045897 creator A5058670321 @default.
• W3159045897 creator A5091395218 @default.
• W3159045897 date "2021-04-29" @default.
• W3159045897 modified "2023-09-27" @default.
• W3159045897 title "You Can Still Achieve Fairness Without Sensitive Attributes: Exploring Biases in Non-Sensitive Features." @default.
• W3159045897 cites W1686708763 @default.
• W3159045897 cites W1766902308 @default.
• W3159045897 cites W2014352947 @default.
• W3159045897 cites W2056671981 @default.
• W3159045897 cites W2076261573 @default.
• W3159045897 cites W2100960835 @default.
• W3159045897 cites W2116984840 @default.
• W3159045897 cites W2126400421 @default.
• W3159045897 cites W2157928966 @default.
• W3159045897 cites W2162670686 @default.
• W3159045897 cites W2530395818 @default.
• W3159045897 cites W2550080458 @default.
• W3159045897 cites W2725155646 @default.
• W3159045897 cites W2780079276 @default.
• W3159045897 cites W2809878087 @default.
• W3159045897 cites W2886848602 @default.
• W3159045897 cites W2888109941 @default.
• W3159045897 cites W2945445411 @default.
• W3159045897 cites W2949200088 @default.
• W3159045897 cites W2954709318 @default.
• W3159045897 cites W2962750142 @default.
• W3159045897 cites W2963053914 @default.
• W3159045897 cites W2963116854 @default.
• W3159045897 cites W2963178340 @default.
• W3159045897 cites W2963588812 @default.
• W3159045897 cites W2963818033 @default.
• W3159045897 cites W2969896603 @default.
• W3159045897 cites W2980688251 @default.
• W3159045897 cites W2989701728 @default.
• W3159045897 cites W3013460382 @default.
• W3159045897 cites W3080365325 @default.
• W3159045897 cites W3094239814 @default.
• W3159045897 cites W3099803834 @default.
• W3159045897 cites W3117178429 @default.
• W3159045897 hasPublicationYear "2021" @default.
• W3159045897 type Work @default.
• W3159045897 sameAs 3159045897 @default.
• W3159045897 citedByCount "1" @default.
• W3159045897 countsByYear W31590458972022 @default.
• W3159045897 crossrefType "posted-content" @default.
• W3159045897 hasAuthorship W3159045897A5011048500 @default.
• W3159045897 hasAuthorship W3159045897A5053042660 @default.
• W3159045897 hasAuthorship W3159045897A5058670321 @default.
• W3159045897 hasAuthorship W3159045897A5091395218 @default.
• W3159045897 hasConcept C119857082 @default.
• W3159045897 hasConcept C124101348 @default.
• W3159045897 hasConcept C138885662 @default.
• W3159045897 hasConcept C154945302 @default.
• W3159045897 hasConcept C2776401178 @default.
• W3159045897 hasConcept C2777673361 @default.
• W3159045897 hasConcept C41008148 @default.
• W3159045897 hasConcept C41895202 @default.
• W3159045897 hasConcept C51632099 @default.
• W3159045897 hasConcept C95623464 @default.
• W3159045897 hasConceptScore W3159045897C119857082 @default.
• W3159045897 hasConceptScore W3159045897C124101348 @default.
• W3159045897 hasConceptScore W3159045897C138885662 @default.
• W3159045897 hasConceptScore W3159045897C154945302 @default.
• W3159045897 hasConceptScore W3159045897C2776401178 @default.
• W3159045897 hasConceptScore W3159045897C2777673361 @default.
• W3159045897 hasConceptScore W3159045897C41008148 @default.
• W3159045897 hasConceptScore W3159045897C41895202 @default.
• W3159045897 hasConceptScore W3159045897C51632099 @default.
• W3159045897 hasConceptScore W3159045897C95623464 @default.
• W3159045897 hasLocation W31590458971 @default.
• W3159045897 hasOpenAccess W3159045897 @default.
• W3159045897 hasPrimaryLocation W31590458971 @default.
• W3159045897 hasRelatedWork W2562668640 @default.
• W3159045897 hasRelatedWork W2732051667 @default.
• W3159045897 hasRelatedWork W2895786087 @default.
• W3159045897 hasRelatedWork W2949225910 @default.
• W3159045897 hasRelatedWork W2979327556 @default.
• W3159045897 hasRelatedWork W2982134689 @default.
• W3159045897 hasRelatedWork W2984656972 @default.
• W3159045897 hasRelatedWork W3004865980 @default.
• W3159045897 hasRelatedWork W3035422508 @default.
• W3159045897 hasRelatedWork W3037546814 @default.
• W3159045897 hasRelatedWork W3088969596 @default.
• W3159045897 hasRelatedWork W3094866301 @default.
• W3159045897 hasRelatedWork W3113348680 @default.
• W3159045897 hasRelatedWork W3135636354 @default.
• W3159045897 hasRelatedWork W3172756206 @default.
• W3159045897 hasRelatedWork W3177106777 @default.
• W3159045897 hasRelatedWork W3200944305 @default.
• W3159045897 hasRelatedWork W3202444514 @default.
• W3159045897 hasRelatedWork W3206122349 @default.
• W3159045897 hasRelatedWork W825630075 @default.
• W3159045897 isParatext "false" @default.
• W3159045897 isRetracted "false" @default.
• W3159045897 magId "3159045897" @default.
• W3159045897 workType "article" @default.