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

Online learning to rank (OL2R) has attracted great research interests inrecent years, thanks to its advantages in avoiding expensive relevance labelingas required in offline supervised ranking model learning. Such a solutionexplores the unknowns (e.g., intentionally present selected results on toppositions) to improve its relevance estimation. This however triggers concernson its ranking fairness: different groups of items might receive differentialtreatments during the course of OL2R. But existing fair ranking solutionsusually require the knowledge of result relevance or a performing rankerbeforehand, which contradicts with the setting of OL2R and thus cannot bedirectly applied to guarantee fairness.  In this work, we propose a general framework to achieve fairness defined bygroup exposure in OL2R. The key idea is to calibrate exploration andexploitation for fairness control, relevance learning and online rankingquality. In particular, when the model is exploring a set of results forrelevance feedback, we confine the exploration within a subset of randompermutations, where fairness across groups is maintained while the feedback isstill unbiased. Theoretically we prove such a strategy introduces minimumdistortion in OL2R's regret to obtain fairness. Extensive empirical analysis isperformed on two public learning to rank benchmark datasets to demonstrate theeffectiveness of the proposed solution compared to existing fair OL2Rsolutions.

Calibrating Explore-Exploit Trade-off for Fair Online Learning to Rank