Matches in SemOpenAlex for { <https://semopenalex.org/work/W3132110306> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3132110306 abstract "Machine learning models play an important role for decision-making systems in areas such as hiring, insurance, and predictive policing. However, it still remains a challenge to guarantee their trustworthiness. Fairness is one of the most critical properties of these machine learning models, while individual discriminatory cases may break the trustworthiness of these systems severely. In this paper, we present a systematic approach of testing the fairness of a machine learning model, with individual discriminatory inputs generated automatically in an adaptive manner based on the state-of-the-art deep reinforcement learning techniques. Our approach can explore and exploit the input space efficiently, and find more individual discriminatory inputs within less time consumption. Case studies with typical benchmark models demonstrate the effectiveness and efficiency of our approach, compared to the state-of-the-art black-box fairness testing approaches." @default.
- W3132110306 created "2021-03-01" @default.
- W3132110306 creator A5016249842 @default.
- W3132110306 creator A5030772308 @default.
- W3132110306 date "2020-12-01" @default.
- W3132110306 modified "2023-09-26" @default.
- W3132110306 title "Fairness Testing of Machine Learning Models Using Deep Reinforcement Learning" @default.
- W3132110306 cites W2100960835 @default.
- W3132110306 cites W2127412976 @default.
- W3132110306 cites W2516809705 @default.
- W3132110306 cites W2559767995 @default.
- W3132110306 cites W2575705757 @default.
- W3132110306 cites W2581465409 @default.
- W3132110306 cites W2730550703 @default.
- W3132110306 cites W2766447205 @default.
- W3132110306 cites W2788295351 @default.
- W3132110306 cites W2806400877 @default.
- W3132110306 cites W2809701591 @default.
- W3132110306 cites W2886249837 @default.
- W3132110306 cites W2898304221 @default.
- W3132110306 cites W2898557219 @default.
- W3132110306 cites W2910603373 @default.
- W3132110306 cites W2967682612 @default.
- W3132110306 cites W3043122026 @default.
- W3132110306 cites W3100789280 @default.
- W3132110306 cites W3105041635 @default.
- W3132110306 doi "https://doi.org/10.1109/trustcom50675.2020.00029" @default.
- W3132110306 hasPublicationYear "2020" @default.
- W3132110306 type Work @default.
- W3132110306 sameAs 3132110306 @default.
- W3132110306 citedByCount "1" @default.
- W3132110306 countsByYear W31321103062023 @default.
- W3132110306 crossrefType "proceedings-article" @default.
- W3132110306 hasAuthorship W3132110306A5016249842 @default.
- W3132110306 hasAuthorship W3132110306A5030772308 @default.
- W3132110306 hasConcept C105795698 @default.
- W3132110306 hasConcept C119857082 @default.
- W3132110306 hasConcept C13280743 @default.
- W3132110306 hasConcept C153701036 @default.
- W3132110306 hasConcept C154945302 @default.
- W3132110306 hasConcept C165696696 @default.
- W3132110306 hasConcept C185798385 @default.
- W3132110306 hasConcept C205649164 @default.
- W3132110306 hasConcept C33923547 @default.
- W3132110306 hasConcept C38652104 @default.
- W3132110306 hasConcept C41008148 @default.
- W3132110306 hasConcept C72434380 @default.
- W3132110306 hasConcept C94966114 @default.
- W3132110306 hasConcept C97541855 @default.
- W3132110306 hasConceptScore W3132110306C105795698 @default.
- W3132110306 hasConceptScore W3132110306C119857082 @default.
- W3132110306 hasConceptScore W3132110306C13280743 @default.
- W3132110306 hasConceptScore W3132110306C153701036 @default.
- W3132110306 hasConceptScore W3132110306C154945302 @default.
- W3132110306 hasConceptScore W3132110306C165696696 @default.
- W3132110306 hasConceptScore W3132110306C185798385 @default.
- W3132110306 hasConceptScore W3132110306C205649164 @default.
- W3132110306 hasConceptScore W3132110306C33923547 @default.
- W3132110306 hasConceptScore W3132110306C38652104 @default.
- W3132110306 hasConceptScore W3132110306C41008148 @default.
- W3132110306 hasConceptScore W3132110306C72434380 @default.
- W3132110306 hasConceptScore W3132110306C94966114 @default.
- W3132110306 hasConceptScore W3132110306C97541855 @default.
- W3132110306 hasFunder F4320335777 @default.
- W3132110306 hasLocation W31321103061 @default.
- W3132110306 hasOpenAccess W3132110306 @default.
- W3132110306 hasPrimaryLocation W31321103061 @default.
- W3132110306 hasRelatedWork W2729602312 @default.
- W3132110306 hasRelatedWork W2951006695 @default.
- W3132110306 hasRelatedWork W2967682612 @default.
- W3132110306 hasRelatedWork W3022038857 @default.
- W3132110306 hasRelatedWork W3095449511 @default.
- W3132110306 hasRelatedWork W3132110306 @default.
- W3132110306 hasRelatedWork W3141495010 @default.
- W3132110306 hasRelatedWork W4318621078 @default.
- W3132110306 hasRelatedWork W4319083788 @default.
- W3132110306 hasRelatedWork W4379255972 @default.
- W3132110306 isParatext "false" @default.
- W3132110306 isRetracted "false" @default.
- W3132110306 magId "3132110306" @default.
- W3132110306 workType "article" @default.