FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035729345> ?p ?o ?g. }

• W3035729345 abstract "Optimizing prediction accuracy can come at the expense of fairness. Towards minimizing discrimination against a group, fair machine learning algorithms strive to equalize the behavior of a model across different groups, by imposing a fairness constraint on models. However, we show that giving the same importance to groups of different sizes and distributions, to counteract the effect of bias in training data, can be in conflict with robustness. We analyze data poisoning attacks against group-based fair machine learning, with the focus on equalized odds. An adversary who can control sampling or labeling for a fraction of training data, can reduce the test accuracy significantly beyond what he can achieve on unconstrained models. Adversarial sampling and adversarial labeling attacks can also worsen the model's fairness gap on test data, even though the model satisfies the fairness constraint on training data. We analyze the robustness of fair machine learning through an empirical evaluation of attacks on multiple algorithms and benchmark datasets." @default.
• W3035729345 created "2020-06-19" @default.
• W3035729345 creator A5002058716 @default.
• W3035729345 creator A5026682474 @default.
• W3035729345 creator A5036259251 @default.
• W3035729345 creator A5084892128 @default.
• W3035729345 creator A5091522099 @default.
• W3035729345 date "2020-06-15" @default.
• W3035729345 modified "2023-09-27" @default.
• W3035729345 title "On Adversarial Bias and the Robustness of Fair Machine Learning" @default.
• W3035729345 cites W1839515685 @default.
• W3035729345 cites W2015317001 @default.
• W3035729345 cites W2040825624 @default.
• W3035729345 cites W2100960835 @default.
• W3035729345 cites W2116666691 @default.
• W3035729345 cites W2118025696 @default.
• W3035729345 cites W2293844262 @default.
• W3035729345 cites W2513180554 @default.
• W3035729345 cites W2530395818 @default.
• W3035729345 cites W2540757487 @default.
• W3035729345 cites W2584805976 @default.
• W3035729345 cites W2597603852 @default.
• W3035729345 cites W2602110945 @default.
• W3035729345 cites W2748789698 @default.
• W3035729345 cites W2753845591 @default.
• W3035729345 cites W2774423163 @default.
• W3035729345 cites W2788416960 @default.
• W3035729345 cites W2790744245 @default.
• W3035729345 cites W2809969113 @default.
• W3035729345 cites W2898998737 @default.
• W3035729345 cites W290150691 @default.
• W3035729345 cites W2909334458 @default.
• W3035729345 cites W2949506549 @default.
• W3035729345 cites W2962763344 @default.
• W3035729345 cites W2963343288 @default.
• W3035729345 cites W2963351127 @default.
• W3035729345 cites W2963777610 @default.
• W3035729345 cites W2963803533 @default.
• W3035729345 cites W2963888996 @default.
• W3035729345 cites W2963903822 @default.
• W3035729345 cites W2963940658 @default.
• W3035729345 cites W2970642535 @default.
• W3035729345 cites W3023309920 @default.
• W3035729345 cites W3031684522 @default.
• W3035729345 cites W3046916097 @default.
• W3035729345 cites W3120740533 @default.
• W3035729345 cites W3181414820 @default.
• W3035729345 hasPublicationYear "2020" @default.
• W3035729345 type Work @default.
• W3035729345 sameAs 3035729345 @default.
• W3035729345 citedByCount "13" @default.
• W3035729345 countsByYear W30357293452020 @default.
• W3035729345 countsByYear W30357293452021 @default.
• W3035729345 crossrefType "posted-content" @default.
• W3035729345 hasAuthorship W3035729345A5002058716 @default.
• W3035729345 hasAuthorship W3035729345A5026682474 @default.
• W3035729345 hasAuthorship W3035729345A5036259251 @default.
• W3035729345 hasAuthorship W3035729345A5084892128 @default.
• W3035729345 hasAuthorship W3035729345A5091522099 @default.
• W3035729345 hasConcept C104317684 @default.
• W3035729345 hasConcept C105795698 @default.
• W3035729345 hasConcept C119857082 @default.
• W3035729345 hasConcept C120936955 @default.
• W3035729345 hasConcept C13280743 @default.
• W3035729345 hasConcept C143095724 @default.
• W3035729345 hasConcept C151956035 @default.
• W3035729345 hasConcept C154945302 @default.
• W3035729345 hasConcept C16910744 @default.
• W3035729345 hasConcept C185592680 @default.
• W3035729345 hasConcept C185798385 @default.
• W3035729345 hasConcept C199360897 @default.
• W3035729345 hasConcept C205649164 @default.
• W3035729345 hasConcept C33923547 @default.
• W3035729345 hasConcept C37736160 @default.
• W3035729345 hasConcept C38652104 @default.
• W3035729345 hasConcept C41008148 @default.
• W3035729345 hasConcept C41065033 @default.
• W3035729345 hasConcept C51632099 @default.
• W3035729345 hasConcept C55493867 @default.
• W3035729345 hasConcept C63479239 @default.
• W3035729345 hasConceptScore W3035729345C104317684 @default.
• W3035729345 hasConceptScore W3035729345C105795698 @default.
• W3035729345 hasConceptScore W3035729345C119857082 @default.
• W3035729345 hasConceptScore W3035729345C120936955 @default.
• W3035729345 hasConceptScore W3035729345C13280743 @default.
• W3035729345 hasConceptScore W3035729345C143095724 @default.
• W3035729345 hasConceptScore W3035729345C151956035 @default.
• W3035729345 hasConceptScore W3035729345C154945302 @default.
• W3035729345 hasConceptScore W3035729345C16910744 @default.
• W3035729345 hasConceptScore W3035729345C185592680 @default.
• W3035729345 hasConceptScore W3035729345C185798385 @default.
• W3035729345 hasConceptScore W3035729345C199360897 @default.
• W3035729345 hasConceptScore W3035729345C205649164 @default.
• W3035729345 hasConceptScore W3035729345C33923547 @default.
• W3035729345 hasConceptScore W3035729345C37736160 @default.
• W3035729345 hasConceptScore W3035729345C38652104 @default.
• W3035729345 hasConceptScore W3035729345C41008148 @default.
• W3035729345 hasConceptScore W3035729345C41065033 @default.
• W3035729345 hasConceptScore W3035729345C51632099 @default.
• W3035729345 hasConceptScore W3035729345C55493867 @default.

• next