Matches in SemOpenAlex for { <https://semopenalex.org/work/W3114562264> ?p ?o ?g. }
- W3114562264 abstract "Anomaly detection aims to find instances that are considered unusual and is a fundamental problem of data science. Recently, deep anomaly detection methods were shown to achieve superior results particularly in complex data such as images. Our work focuses on deep one-class classification for anomaly detection which learns a mapping only from the normal samples. However, the non-linear transformation performed by deep learning can potentially find patterns associated with social bias. The challenge with adding fairness to deep anomaly detection is to ensure both making fair and correct anomaly predictions simultaneously. In this paper, we propose a new architecture for the fair anomaly detection approach (Deep Fair SVDD) and train it using an adversarial network to de-correlate the relationships between the sensitive attributes and the learned representations. This differs from how fairness is typically added namely as a regularizer or a constraint. Further, we propose two effective fairness measures and empirically demonstrate that existing deep anomaly detection methods are unfair. We show that our proposed approach can remove the unfairness largely with minimal loss on the anomaly detection performance. Lastly, we conduct an in-depth analysis to show the strength and limitations of our proposed model, including parameter analysis, feature visualization, and run-time analysis." @default.
- W3114562264 created "2021-01-05" @default.
- W3114562264 creator A5022289938 @default.
- W3114562264 creator A5030289182 @default.
- W3114562264 date "2020-12-29" @default.
- W3114562264 modified "2023-09-24" @default.
- W3114562264 title "Towards Fair Deep Anomaly Detection" @default.
- W3114562264 cites W1834627138 @default.
- W3114562264 cites W1836465849 @default.
- W3114562264 cites W1876967670 @default.
- W3114562264 cites W2099471712 @default.
- W3114562264 cites W2122646361 @default.
- W3114562264 cites W2127979711 @default.
- W3114562264 cites W2132870739 @default.
- W3114562264 cites W2136655611 @default.
- W3114562264 cites W2143559571 @default.
- W3114562264 cites W2144182447 @default.
- W3114562264 cites W2187089797 @default.
- W3114562264 cites W2204904589 @default.
- W3114562264 cites W2340896621 @default.
- W3114562264 cites W2599354622 @default.
- W3114562264 cites W2621614835 @default.
- W3114562264 cites W2725155646 @default.
- W3114562264 cites W2787947370 @default.
- W3114562264 cites W2888161220 @default.
- W3114562264 cites W2897978524 @default.
- W3114562264 cites W2910068345 @default.
- W3114562264 cites W2929382047 @default.
- W3114562264 cites W2949848919 @default.
- W3114562264 cites W2962742544 @default.
- W3114562264 cites W2963100392 @default.
- W3114562264 cites W2963116854 @default.
- W3114562264 cites W2963773039 @default.
- W3114562264 cites W2963803533 @default.
- W3114562264 cites W2963992001 @default.
- W3114562264 cites W2971015439 @default.
- W3114562264 cites W2989929945 @default.
- W3114562264 cites W2990988059 @default.
- W3114562264 cites W2995458562 @default.
- W3114562264 cites W3002138439 @default.
- W3114562264 cites W3003545719 @default.
- W3114562264 cites W3012963798 @default.
- W3114562264 cites W3013973393 @default.
- W3114562264 cites W3023309920 @default.
- W3114562264 cites W3049447432 @default.
- W3114562264 cites W3090138545 @default.
- W3114562264 cites W3153872861 @default.
- W3114562264 cites W584462734 @default.
- W3114562264 doi "https://doi.org/10.48550/arxiv.2012.14961" @default.
- W3114562264 hasPublicationYear "2020" @default.
- W3114562264 type Work @default.
- W3114562264 sameAs 3114562264 @default.
- W3114562264 citedByCount "1" @default.
- W3114562264 countsByYear W31145622642021 @default.
- W3114562264 crossrefType "posted-content" @default.
- W3114562264 hasAuthorship W3114562264A5022289938 @default.
- W3114562264 hasAuthorship W3114562264A5030289182 @default.
- W3114562264 hasBestOaLocation W31145622641 @default.
- W3114562264 hasConcept C104317684 @default.
- W3114562264 hasConcept C108583219 @default.
- W3114562264 hasConcept C119857082 @default.
- W3114562264 hasConcept C121332964 @default.
- W3114562264 hasConcept C124101348 @default.
- W3114562264 hasConcept C12997251 @default.
- W3114562264 hasConcept C138885662 @default.
- W3114562264 hasConcept C153180895 @default.
- W3114562264 hasConcept C154945302 @default.
- W3114562264 hasConcept C185592680 @default.
- W3114562264 hasConcept C204241405 @default.
- W3114562264 hasConcept C2524010 @default.
- W3114562264 hasConcept C26873012 @default.
- W3114562264 hasConcept C2776036281 @default.
- W3114562264 hasConcept C2776401178 @default.
- W3114562264 hasConcept C33923547 @default.
- W3114562264 hasConcept C36464697 @default.
- W3114562264 hasConcept C41008148 @default.
- W3114562264 hasConcept C41895202 @default.
- W3114562264 hasConcept C55493867 @default.
- W3114562264 hasConcept C739882 @default.
- W3114562264 hasConceptScore W3114562264C104317684 @default.
- W3114562264 hasConceptScore W3114562264C108583219 @default.
- W3114562264 hasConceptScore W3114562264C119857082 @default.
- W3114562264 hasConceptScore W3114562264C121332964 @default.
- W3114562264 hasConceptScore W3114562264C124101348 @default.
- W3114562264 hasConceptScore W3114562264C12997251 @default.
- W3114562264 hasConceptScore W3114562264C138885662 @default.
- W3114562264 hasConceptScore W3114562264C153180895 @default.
- W3114562264 hasConceptScore W3114562264C154945302 @default.
- W3114562264 hasConceptScore W3114562264C185592680 @default.
- W3114562264 hasConceptScore W3114562264C204241405 @default.
- W3114562264 hasConceptScore W3114562264C2524010 @default.
- W3114562264 hasConceptScore W3114562264C26873012 @default.
- W3114562264 hasConceptScore W3114562264C2776036281 @default.
- W3114562264 hasConceptScore W3114562264C2776401178 @default.
- W3114562264 hasConceptScore W3114562264C33923547 @default.
- W3114562264 hasConceptScore W3114562264C36464697 @default.
- W3114562264 hasConceptScore W3114562264C41008148 @default.
- W3114562264 hasConceptScore W3114562264C41895202 @default.
- W3114562264 hasConceptScore W3114562264C55493867 @default.
- W3114562264 hasConceptScore W3114562264C739882 @default.