Adaptively sharing multi-levels of distributed representations in multi-task learning

Tianxin Wang, Fuzhen Zhuang, Ying Sun, Xiangliang Zhang, Leyu Lin, Feng Xia, Lei He, Qing He

Research output: Contribution to journalArticlepeer-review

5 Scopus citations


In multi-task learning, the performance is often sensitive to the relationships between tasks. Thus it is important to study how to exploit the complex relationships across different tasks. One line of research captures the complex task relationships, by increasing the model capacity and thus requiring a large training dataset. However in many real-world applications, the amount of labeled data is limited. In this paper, we propose a light weight and specially designed architecture, which aims to model task relationships for small or middle-sized datasets. The proposed framework learns a task-specific ensemble of sub-networks in different depths, and is able to adapt the model architecture for the given data. The task-specific ensemble parameters are learned simultaneously with the weights of the network by optimizing a single loss function defined with respect to the end task. The hierarchical model structure is able to share both general and specific distributed representations to capture the inherent relationships between tasks. We validate our approach on various types of tasks, including synthetic task, article recommendation task and vision task. The results demonstrate the advantages of our model over several competitive baselines especially when the tasks are less-related.
Original languageEnglish (US)
Pages (from-to)226-234
Number of pages9
JournalInformation Sciences
StatePublished - Apr 1 2022
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2023-09-20

ASJC Scopus subject areas

  • Artificial Intelligence
  • Theoretical Computer Science
  • Software
  • Information Systems and Management
  • Control and Systems Engineering
  • Computer Science Applications


Dive into the research topics of 'Adaptively sharing multi-levels of distributed representations in multi-task learning'. Together they form a unique fingerprint.

Cite this