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

When a number of similar tasks have to be learned simultaneously, multi-tasklearning (MTL) models can attain significantly higher accuracy than single-tasklearning (STL) models. However, the advantage of MTL depends on variousfactors, such as the similarity of the tasks, the sizes of the datasets, and soon; in fact, some tasks might not benefit from MTL and may even incur a loss ofaccuracy compared to STL. Hence, the question arises: which tasks should belearned together? Domain experts can attempt to group tasks together followingintuition, experience, and best practices, but manual grouping can belabor-intensive and far from optimal. In this paper, we propose a novelautomated approach for task grouping. First, we study the affinity of tasks forMTL using four benchmark datasets that have been used extensively in the MTLliterature, focusing on neural network-based MTL models. We identify inherenttask features and STL characteristics that can help us to predict whether agroup of tasks should be learned together using MTL or if they should belearned independently using STL. Building on this predictor, we introduce arandomized search algorithm, which employs the predictor to minimize the numberof MTL trainings performed during the search for task groups. We demonstrate onthe four benchmark datasets that our predictor-driven search approach can findbetter task groupings than existing baseline approaches.

Task Grouping for Automated Multi-Task Machine Learning via Task Affinity Prediction