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

In document classification for, e.g., legal and biomedical text, we oftendeal with hundreds of classes, including very infrequent ones, as well astemporal concept drift caused by the influence of real world events, e.g.,policy changes, conflicts, or pandemics. Class imbalance and drift cansometimes be mitigated by resampling the training data to simulate (orcompensate for) a known target distribution, but what if the targetdistribution is determined by unknown future events? Instead of simplyresampling uniformly to hedge our bets, we focus on the underlying optimizationalgorithms used to train such document classifiers and evaluate severalgroup-robust optimization algorithms, initially proposed to mitigategroup-level disparities. Reframing group-robust algorithms as adaptationalgorithms under concept drift, we find that Invariant Risk Minimization andSpectral Decoupling outperform sampling-based approaches to class imbalance andconcept drift, and lead to much better performance on minority classes. Theeffect is more pronounced the larger the label set.

Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting