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/

Zendy Plus

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

Zendy Tools

Zendy Open

In multi-label learning, a particular case of multi-task learning where asingle data point is associated with multiple target labels, it was widelyassumed in the literature that, to obtain best accuracy, the dependence amongthe labels should be explicitly modeled. This premise led to a proliferation ofmethods offering techniques to learn and predict labels together, for examplewhere the prediction for one label influences predictions for other labels.Even though it is now acknowledged that in many contexts a model of dependenceis not required for optimal performance, such models continue to outperformindependent models in some of those very contexts, suggesting alternativeexplanations for their performance beyond label dependence, which theliterature is only recently beginning to unravel. Leveraging and extendingrecent discoveries, we turn the original premise of multi-label learning on itshead, and approach the problem of joint-modeling specifically under the absenceof any measurable dependence among task labels; for example, when task labelscome from separate problem domains. We shift insights from this study towardsbuilding an approach for transfer learning that challenges the long-heldassumption that transferability of tasks comes from measurements of similaritybetween the source and target domains or models. This allows us to design andtest a method for transfer learning, which is model driven rather than purelydata driven, and furthermore it is black box and model-agnostic (any base modelclass can be considered). We show that essentially we can createtask-dependence based on source-model capacity. The results we obtain haveimportant implications and provide clear directions for future work, both inthe areas of multi-label and transfer learning.

From Multi-label Learning to Cross-Domain Transfer: A Model-Agnostic Approach