Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387211036> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4387211036 endingPage "317" @default.
- W4387211036 startingPage "307" @default.
- W4387211036 abstract "Deep learning is becoming increasingly ubiquitous in medical research and applications while involving sensitive information and even critical diagnosis decisions. Researchers observe a significant performance disparity among subgroups with different demographic attributes, which is called model unfairness, and put lots of effort into carefully designing elegant architectures to address unfairness, which poses heavy training burden, brings poor generalization, and reveals the trade-off between model performance and fairness. To tackle these issues, we propose FairAdaBN by making batch normalization adaptive to sensitive attributes. This simple but effective design can be adapted to several classification backbones that are originally unaware of fairness. Additionally, we derive a novel loss function that restrains statistical parity between subgroups on mini-batches, encouraging the model to converge with considerable fairness. In order to evaluate the trade-off between model performance and fairness, we propose a new metric, named Fairness-Accuracy Trade-off Efficiency (FATE), to compute normalized fairness improvement over accuracy drop. Experiments on two dermatological datasets show that our proposed method outperforms other methods on fairness criteria and FATE. Our code is available at https://github.com/XuZikang/FairAdaBN ." @default.
- W4387211036 created "2023-10-01" @default.
- W4387211036 creator A5013741499 @default.
- W4387211036 creator A5016667706 @default.
- W4387211036 creator A5058029021 @default.
- W4387211036 creator A5080071268 @default.
- W4387211036 creator A5088081535 @default.
- W4387211036 date "2023-01-01" @default.
- W4387211036 modified "2023-10-01" @default.
- W4387211036 title "FairAdaBN: Mitigating Unfairness with Adaptive Batch Normalization and Its Application to Dermatological Disease Classification" @default.
- W4387211036 cites W2100960835 @default.
- W4387211036 cites W2963946669 @default.
- W4387211036 cites W3034256900 @default.
- W4387211036 cites W3088542089 @default.
- W4387211036 cites W3091268787 @default.
- W4387211036 cites W3102785203 @default.
- W4387211036 cites W3109762849 @default.
- W4387211036 cites W3110181119 @default.
- W4387211036 cites W3134475970 @default.
- W4387211036 cites W3135353679 @default.
- W4387211036 cites W3175547470 @default.
- W4387211036 cites W3190939658 @default.
- W4387211036 cites W3203636625 @default.
- W4387211036 cites W4225806553 @default.
- W4387211036 cites W4295793620 @default.
- W4387211036 cites W4295795871 @default.
- W4387211036 cites W4308764909 @default.
- W4387211036 cites W4312533901 @default.
- W4387211036 cites W4379767400 @default.
- W4387211036 doi "https://doi.org/10.1007/978-3-031-43895-0_29" @default.
- W4387211036 hasPublicationYear "2023" @default.
- W4387211036 type Work @default.
- W4387211036 citedByCount "0" @default.
- W4387211036 crossrefType "book-chapter" @default.
- W4387211036 hasAuthorship W4387211036A5013741499 @default.
- W4387211036 hasAuthorship W4387211036A5016667706 @default.
- W4387211036 hasAuthorship W4387211036A5058029021 @default.
- W4387211036 hasAuthorship W4387211036A5080071268 @default.
- W4387211036 hasAuthorship W4387211036A5088081535 @default.
- W4387211036 hasConcept C119857082 @default.
- W4387211036 hasConcept C134306372 @default.
- W4387211036 hasConcept C136886441 @default.
- W4387211036 hasConcept C144024400 @default.
- W4387211036 hasConcept C154945302 @default.
- W4387211036 hasConcept C162324750 @default.
- W4387211036 hasConcept C176217482 @default.
- W4387211036 hasConcept C177148314 @default.
- W4387211036 hasConcept C19165224 @default.
- W4387211036 hasConcept C21547014 @default.
- W4387211036 hasConcept C33923547 @default.
- W4387211036 hasConcept C41008148 @default.
- W4387211036 hasConceptScore W4387211036C119857082 @default.
- W4387211036 hasConceptScore W4387211036C134306372 @default.
- W4387211036 hasConceptScore W4387211036C136886441 @default.
- W4387211036 hasConceptScore W4387211036C144024400 @default.
- W4387211036 hasConceptScore W4387211036C154945302 @default.
- W4387211036 hasConceptScore W4387211036C162324750 @default.
- W4387211036 hasConceptScore W4387211036C176217482 @default.
- W4387211036 hasConceptScore W4387211036C177148314 @default.
- W4387211036 hasConceptScore W4387211036C19165224 @default.
- W4387211036 hasConceptScore W4387211036C21547014 @default.
- W4387211036 hasConceptScore W4387211036C33923547 @default.
- W4387211036 hasConceptScore W4387211036C41008148 @default.
- W4387211036 hasLocation W43872110361 @default.
- W4387211036 hasOpenAccess W4387211036 @default.
- W4387211036 hasPrimaryLocation W43872110361 @default.
- W4387211036 hasRelatedWork W2063185616 @default.
- W4387211036 hasRelatedWork W2885094885 @default.
- W4387211036 hasRelatedWork W2961085424 @default.
- W4387211036 hasRelatedWork W3046775127 @default.
- W4387211036 hasRelatedWork W3170094116 @default.
- W4387211036 hasRelatedWork W4285260836 @default.
- W4387211036 hasRelatedWork W4286629047 @default.
- W4387211036 hasRelatedWork W4306321456 @default.
- W4387211036 hasRelatedWork W4306674287 @default.
- W4387211036 hasRelatedWork W4224009465 @default.
- W4387211036 isParatext "false" @default.
- W4387211036 isRetracted "false" @default.
- W4387211036 workType "book-chapter" @default.