Publication:
Towards Improving Generalization of Multi-Task Learning

ac.person.position HDR Student
ac.person.position Staff
dc.contributor.advisor Lin, Xuemin
dc.contributor.author Mao, Yuren
dc.date.accessioned 2022-02-07T21:36:16Z
dc.date.available 2022-02-07T21:36:16Z
dc.date.issued 2021
dc.description.abstract Multi-task Learning (MTL), which involves the simultaneous learning of multiple tasks, can achieve better performance than learning each task independently. It has achieved great success in various applications, ranging from computer vision to bioinformatics. However, involving multiple tasks in a single learning process is complicated, for both cooperation and competition exist across the including tasks; furthermore, the cooperation boosts the generalization of MTL while the competition degenerates it. There lacks of a systematic study on how to improve MTL's generalization by handling the cooperation and competition. This thesis systematically studies this problem and proposed four novel MTL methods to enhance the between-task cooperation or reduce the between-task competition. Specifically, for the between-task cooperation, adversarial multi-task representation learning (AMTRL) and semi-supervised multi-task learning (Semi-MTL) are studied; furthermore, a novel adaptive AMTRL method and a novel representation consistency regularization-based Semi-MTL method are proposed respectively. As to the between-task competition, this thesis analyzes the task variance and task imbalance; furthermore, a novel task variance regularization-based MTL method and a novel task-imbalance-aware MTL method are proposed respectively. The above proposed methods can improve the generalization of MTL and achieve state-of-the-art performance in real-word MTL applications.
dc.identifier.uri http://hdl.handle.net/1959.4/100064
dc.language English
dc.language.iso en
dc.publisher UNSW, Sydney
dc.rights CC BY 4.0
dc.rights.uri https://creativecommons.org/licenses/by/4.0/
dc.subject.other Multi-task Learning
dc.title Towards Improving Generalization of Multi-Task Learning
dc.type Thesis
dcterms.accessRights open access
dcterms.rightsHolder Mao, Yuren
dspace.entity.type Publication
unsw.accessRights.uri https://purl.org/coar/access_right/c_abf2
unsw.identifier.doi https://doi.org/10.26190/unsworks/1974
unsw.relation.faculty Engineering
unsw.relation.school School of Computer Science and Engineering
unsw.relation.school School of Computer Science and Engineering
unsw.subject.fieldofresearchcode 4611 Machine learning
unsw.thesis.degreetype PhD Doctorate
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
public version.pdf
Size:
4.66 MB
Format:
application/pdf
Description:
Resource type