To extend our understanding of individual student knowledge sharing, we apply organizational knowledge sharing literature to classroom settings. Using data from 111 students representing 25 groups, we investigated the individual knowledge sharing process. Results show that task self-efficacy and expectation of reciprocal knowledge sharing from group members positively predicted intent to share ...

Three-quarters of the global mental health burden exists in low- and middle-income countries (LMICs), yet the lack of mental health services in resource-poor settings is striking. Task-sharing (also, task-shifting), where mental health care is provided by non-specialists, has been proposed to improve access to mental health care in LMICs. This multi-site qualitative study investigates the accep...

Most contemporary multi-task learning methods assume linear models. This setting is considered shallow in the era of deep learning. In this paper, we present a new deep multi-task representation learning framework that learns cross-task sharing structure at every layer in a deep network. Our approach is based on generalising the matrix factorisation techniques explicitly or implicitly used by m...

Abstract State-of-the-art deep neural network plays an increasingly important role in artificial intelligence, while the huge number of parameters networks brings high memory cost and computational complexity. To solve this problem, filter pruning is widely used for compression acceleration. However, existing algorithms focus mainly on single model, few results are available to multi-task that ...

In the context of Multi-access Edge Computing (MEC), task sharing mechanism among edge servers is an activity vital importance for speeding up computing process and thereby improving user experience. The distributed resources in form are expected to collaborate with each other order boost overall performance a MEC system. However, there many challenges adopt global collaboration server entities...