Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367000359> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4367000359 abstract "Improving the fairness of machine learning models is a nuanced task that requires decision makers to reason about multiple, conflicting criteria. The majority of fair machine learning methods transform the error-fairness trade-off into a single objective problem with a parameter controlling the relative importance of error versus fairness. We propose instead to directly optimize the error-fairness tradeoff by using multi-objective optimization. We present a flexible framework for defining the fair machine learning task as a weighted classification problem with multiple cost functions. This framework is agnostic to the underlying prediction model as well as the metrics. We use multiobjective optimization to define the sample weights used in model training for a given machine learner, and adapt the weights to optimize multiple metrics of fairness and accuracy across a set of tasks. To reduce the number of optimized parameters, and to constrain their complexity with respect to population subgroups, we propose a novel meta-model approach that learns to map protected attributes to sample weights, rather than optimizing those weights directly. On a set of real-world problems, this approach outperforms current state-of-the-art methods by finding solution sets with preferable error/fairness trade-offs." @default.
- W4367000359 created "2023-04-27" @default.
- W4367000359 creator A5002465837 @default.
- W4367000359 date "2023-07-12" @default.
- W4367000359 modified "2023-09-25" @default.
- W4367000359 title "Optimizing fairness tradeoffs in machine learning with multiobjective meta-models" @default.
- W4367000359 cites W1808460590 @default.
- W4367000359 cites W2040825624 @default.
- W4367000359 cites W2100960835 @default.
- W4367000359 cites W2116984840 @default.
- W4367000359 cites W2167159964 @default.
- W4367000359 cites W2599025709 @default.
- W4367000359 cites W2963116854 @default.
- W4367000359 cites W2981869278 @default.
- W4367000359 cites W2991598122 @default.
- W4367000359 cites W3021613070 @default.
- W4367000359 cites W3100438926 @default.
- W4367000359 cites W3102476541 @default.
- W4367000359 cites W3136561289 @default.
- W4367000359 cites W3197709042 @default.
- W4367000359 cites W4285805255 @default.
- W4367000359 doi "https://doi.org/10.1145/3583131.3590487" @default.
- W4367000359 hasPublicationYear "2023" @default.
- W4367000359 type Work @default.
- W4367000359 citedByCount "0" @default.
- W4367000359 crossrefType "proceedings-article" @default.
- W4367000359 hasAuthorship W4367000359A5002465837 @default.
- W4367000359 hasBestOaLocation W43670003591 @default.
- W4367000359 hasConcept C119857082 @default.
- W4367000359 hasConcept C126255220 @default.
- W4367000359 hasConcept C154945302 @default.
- W4367000359 hasConcept C162324750 @default.
- W4367000359 hasConcept C177264268 @default.
- W4367000359 hasConcept C185592680 @default.
- W4367000359 hasConcept C187736073 @default.
- W4367000359 hasConcept C198531522 @default.
- W4367000359 hasConcept C199360897 @default.
- W4367000359 hasConcept C2780451532 @default.
- W4367000359 hasConcept C33923547 @default.
- W4367000359 hasConcept C41008148 @default.
- W4367000359 hasConcept C43617362 @default.
- W4367000359 hasConcept C68781425 @default.
- W4367000359 hasConceptScore W4367000359C119857082 @default.
- W4367000359 hasConceptScore W4367000359C126255220 @default.
- W4367000359 hasConceptScore W4367000359C154945302 @default.
- W4367000359 hasConceptScore W4367000359C162324750 @default.
- W4367000359 hasConceptScore W4367000359C177264268 @default.
- W4367000359 hasConceptScore W4367000359C185592680 @default.
- W4367000359 hasConceptScore W4367000359C187736073 @default.
- W4367000359 hasConceptScore W4367000359C198531522 @default.
- W4367000359 hasConceptScore W4367000359C199360897 @default.
- W4367000359 hasConceptScore W4367000359C2780451532 @default.
- W4367000359 hasConceptScore W4367000359C33923547 @default.
- W4367000359 hasConceptScore W4367000359C41008148 @default.
- W4367000359 hasConceptScore W4367000359C43617362 @default.
- W4367000359 hasConceptScore W4367000359C68781425 @default.
- W4367000359 hasFunder F4320332161 @default.
- W4367000359 hasLocation W43670003591 @default.
- W4367000359 hasLocation W43670003592 @default.
- W4367000359 hasLocation W43670003593 @default.
- W4367000359 hasOpenAccess W4367000359 @default.
- W4367000359 hasPrimaryLocation W43670003591 @default.
- W4367000359 hasRelatedWork W1491338215 @default.
- W4367000359 hasRelatedWork W1493202049 @default.
- W4367000359 hasRelatedWork W1993518163 @default.
- W4367000359 hasRelatedWork W2058889384 @default.
- W4367000359 hasRelatedWork W2316613179 @default.
- W4367000359 hasRelatedWork W2961085424 @default.
- W4367000359 hasRelatedWork W4286629047 @default.
- W4367000359 hasRelatedWork W4306321456 @default.
- W4367000359 hasRelatedWork W4306674287 @default.
- W4367000359 hasRelatedWork W4224009465 @default.
- W4367000359 isParatext "false" @default.
- W4367000359 isRetracted "false" @default.
- W4367000359 workType "article" @default.