English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent work has emphasized the importance of balancing competing objectivesin model training (e.g., accuracy vs. fairness, or competing measures offairness). Such trade-offs reflect a broader class of multi-objectiveoptimization (MOO) problems in which optimization methods seek Pareto optimaltrade-offs between competing goals. In this work, we first introduce adifferentiable measure that enables direct optimization of group fairness(specifically, balancing accuracy across groups) in model training. Next, wedemonstrate two model-agnostic MOO frameworks for learning Pareto optimalparameterizations over different groups of neural classification models. Weevaluate our methods on the specific task of hate speech detection, in whichprior work has shown lack of group fairness across speakers of differentEnglish dialects. Empirical results across convolutional, sequential, andtransformer-based neural architectures show superior empirical accuracy vs.fairness trade-offs over prior work. More significantly, our measure enablesthe Pareto machinery to ensure that each architecture achieves the bestpossible trade-off between fairness and accuracy w.r.t. the dataset, givenuser-prescribed error tolerance bounds.

Fairly Accurate: Learning Optimal Accuracy vs. Fairness Tradeoffs for Hate Speech Detection