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

Algorithmic fairness has become an important machine learning problem,especially for mission-critical Web applications. This work presents aself-supervised model, called DualFair, that can debias sensitive attributeslike gender and race from learned representations. Unlike existing models thattarget a single type of fairness, our model jointly optimizes for two fairnesscriteria - group fairness and counterfactual fairness - and hence makes fairerpredictions at both the group and individual levels. Our model uses contrastiveloss to generate embeddings that are indistinguishable for each protectedgroup, while forcing the embeddings of counterfactual pairs to be similar. Itthen uses a self-knowledge distillation method to maintain the quality ofrepresentation for the downstream tasks. Extensive analysis over multipledatasets confirms the model's validity and further shows the synergy of jointlyaddressing two fairness criteria, suggesting the model's potential value infair intelligent Web applications.

DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision