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

As the data-driven decision process becomes dominating for industrialapplications, fairness-aware machine learning arouses great attention invarious areas. This work proposes fairness penalties learned by neural networkswith a simple random sampler of sensitive attributes for non-discriminatorysupervised learning. In contrast to many existing works that critically rely onthe discreteness of sensitive attributes and response variables, the proposedpenalty is able to handle versatile formats of the sensitive attributes, so itis more extensively applicable in practice than many existing algorithms. Thispenalty enables us to build a computationally efficient group-levelin-processing fairness-aware training framework. Empirical evidence shows thatour framework enjoys better utility and fairness measures on popular benchmarkdata sets than competing methods. We also theoretically characterize estimationerrors and loss of utility of the proposed neural-penalized risk minimizationproblem.

Fair Supervised Learning with A Simple Random Sampler of Sensitive Attributes