FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3134936382> ?p ?o ?g. }

• W3134936382 abstract "Subset selection algorithms are ubiquitous in AI-driven applications, including, online recruiting portals and image search engines, so it is imperative that these tools are not discriminatory on the basis of protected attributes such as gender or race. Currently, fair subset selection algorithms assume that the protected attributes are known as part of the dataset. However, protected attributes may be noisy due to errors during data collection or if they are imputed (as is often the case in real-world settings). While a wide body of work addresses the effect of noise on the performance of machine learning algorithms, its effect on fairness remains largely unexamined. We find that in the presence of noisy protected attributes, in attempting to increase fairness without considering noise, one can, in fact, decrease the fairness of the result! Towards addressing this, we consider an existing noise model in which there is probabilistic information about the protected attributes (e.g., [19, 32, 44, 56]), and ask is fair selection possible under noisy conditions? We formulate a selection problem which functions for a large class of fairness metrics; given the desired fairness goal, the solution to the denoised problem violates the goal by at most a small multiplicative amount with high probability. Although this denoised problem turns out to be NP-hard, we give a linear-programming based approximation algorithm for it. We evaluate this approach on both synthetic and real-world datasets. Our empirical results show that this approach can produce subsets which significantly improve the fairness metrics despite the presence of noisy protected attributes, and, compared to prior noise-oblivious approaches, has better Pareto-tradeoffs between utility and fairness." @default.
• W3134936382 created "2021-03-15" @default.
• W3134936382 creator A5054251740 @default.
• W3134936382 creator A5065512381 @default.
• W3134936382 date "2021-03-01" @default.
• W3134936382 modified "2023-10-01" @default.
• W3134936382 title "Mitigating Bias in Set Selection with Noisy Protected Attributes" @default.
• W3134936382 cites W1501644705 @default.
• W3134936382 cites W1514928307 @default.
• W3134936382 cites W1973291721 @default.
• W3134936382 cites W1987663912 @default.
• W3134936382 cites W2052138360 @default.
• W3134936382 cites W2069870183 @default.
• W3134936382 cites W2086216108 @default.
• W3134936382 cites W2097246321 @default.
• W3134936382 cites W2102348129 @default.
• W3134936382 cites W2126186592 @default.
• W3134936382 cites W2131492273 @default.
• W3134936382 cites W2149252982 @default.
• W3134936382 cites W2167458573 @default.
• W3134936382 cites W2167460663 @default.
• W3134936382 cites W2167779416 @default.
• W3134936382 cites W2418585934 @default.
• W3134936382 cites W2544318541 @default.
• W3134936382 cites W2666919929 @default.
• W3134936382 cites W2787991113 @default.
• W3134936382 cites W2910883930 @default.
• W3134936382 cites W2950173087 @default.
• W3134936382 cites W2963966702 @default.
• W3134936382 cites W2964751853 @default.
• W3134936382 cites W3012903288 @default.
• W3134936382 cites W3094231124 @default.
• W3134936382 cites W4236127247 @default.
• W3134936382 cites W4244259635 @default.
• W3134936382 doi "https://doi.org/10.1145/3442188.3445887" @default.
• W3134936382 hasPublicationYear "2021" @default.
• W3134936382 type Work @default.
• W3134936382 sameAs 3134936382 @default.
• W3134936382 citedByCount "20" @default.
• W3134936382 countsByYear W31349363822021 @default.
• W3134936382 countsByYear W31349363822022 @default.
• W3134936382 countsByYear W31349363822023 @default.
• W3134936382 crossrefType "proceedings-article" @default.
• W3134936382 hasAuthorship W3134936382A5054251740 @default.
• W3134936382 hasAuthorship W3134936382A5065512381 @default.
• W3134936382 hasBestOaLocation W31349363822 @default.
• W3134936382 hasConcept C115961682 @default.
• W3134936382 hasConcept C119857082 @default.
• W3134936382 hasConcept C124101348 @default.
• W3134936382 hasConcept C134306372 @default.
• W3134936382 hasConcept C154945302 @default.
• W3134936382 hasConcept C177264268 @default.
• W3134936382 hasConcept C199360897 @default.
• W3134936382 hasConcept C2777212361 @default.
• W3134936382 hasConcept C33923547 @default.
• W3134936382 hasConcept C41008148 @default.
• W3134936382 hasConcept C42747912 @default.
• W3134936382 hasConcept C49937458 @default.
• W3134936382 hasConcept C81917197 @default.
• W3134936382 hasConcept C99498987 @default.
• W3134936382 hasConceptScore W3134936382C115961682 @default.
• W3134936382 hasConceptScore W3134936382C119857082 @default.
• W3134936382 hasConceptScore W3134936382C124101348 @default.
• W3134936382 hasConceptScore W3134936382C134306372 @default.
• W3134936382 hasConceptScore W3134936382C154945302 @default.
• W3134936382 hasConceptScore W3134936382C177264268 @default.
• W3134936382 hasConceptScore W3134936382C199360897 @default.
• W3134936382 hasConceptScore W3134936382C2777212361 @default.
• W3134936382 hasConceptScore W3134936382C33923547 @default.
• W3134936382 hasConceptScore W3134936382C41008148 @default.
• W3134936382 hasConceptScore W3134936382C42747912 @default.
• W3134936382 hasConceptScore W3134936382C49937458 @default.
• W3134936382 hasConceptScore W3134936382C81917197 @default.
• W3134936382 hasConceptScore W3134936382C99498987 @default.
• W3134936382 hasLocation W31349363821 @default.
• W3134936382 hasLocation W31349363822 @default.
• W3134936382 hasOpenAccess W3134936382 @default.
• W3134936382 hasPrimaryLocation W31349363821 @default.
• W3134936382 hasRelatedWork W12165144 @default.
• W3134936382 hasRelatedWork W267997 @default.
• W3134936382 hasRelatedWork W5094569 @default.
• W3134936382 hasRelatedWork W6266756 @default.
• W3134936382 hasRelatedWork W7724241 @default.
• W3134936382 hasRelatedWork W7842670 @default.
• W3134936382 hasRelatedWork W7903576 @default.
• W3134936382 hasRelatedWork W7982726 @default.
• W3134936382 hasRelatedWork W8198582 @default.
• W3134936382 hasRelatedWork W9384265 @default.
• W3134936382 isParatext "false" @default.
• W3134936382 isRetracted "false" @default.
• W3134936382 magId "3134936382" @default.
• W3134936382 workType "article" @default.