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

Resilience to class imbalance and confounding biases, together with theassurance of fairness guarantees are highly desirable properties of autonomousdecision-making systems with real-life impact. Many different targetedsolutions have been proposed to address separately these three problems,however a unifying perspective seems to be missing. With this work, we providea general formalization, showing that they are different expressions ofunbalance. Following this intuition, we formulate a unified loss correction toaddress issues related to Fairness, Biases and Imbalances (FBI-loss). Thecorrection capabilities of the proposed approach are assessed on threereal-world benchmarks, each associated to one of the issues underconsideration, and on a family of synthetic data in order to better investigatethe effectiveness of our loss on tasks with different complexities. Theempirical results highlight that the flexible formulation of the FBI-loss leadsalso to competitive performances with respect to literature solutionsspecialised for the single problems.

Addressing Fairness, Bias and Class Imbalance in Machine Learning: the FBI-loss