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

Heterogeneous multi-task learning (HMTL) is an important topic in multi-tasklearning (MTL). Most existing HMTL methods usually solve either scenario whereall tasks reside in the same input (feature) space yet unnecessarily theconsistent output (label) space or scenario where their input (feature) spacesare heterogeneous while the output (label) space is consistent. However, to thebest of our knowledge, there is limited study on twofold heterogeneous MTL(THMTL) scenario where the input and the output spaces are both inconsistent orheterogeneous. In order to handle this complicated scenario, in this paper, wedesign a simple and effective multi-task adaptive learning (MTAL) network tolearn multiple tasks in such THMTL setting. Specifically, we explore andutilize the inherent relationship between tasks for knowledge sharing fromsimilar convolution kernels in individual layers of the MTAL network. Then inorder to realize the sharing, we weightedly aggregate any pair of convolutionalkernels with their similarity greater than some threshold $\rho$, consequently,our model effectively performs cross-task learning while suppresses theintra-redundancy of the entire network. Finally, we conduct end-to-endtraining. Our experimental results demonstrate the effectiveness of our methodin comparison with the state-of-the-art counterparts.

Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs