Unsupervised Multi-task Learning with Hierarchical Data Structure

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

10 Scopus Citations
View graph of relations

Related Research Unit(s)


Original languageEnglish
Pages (from-to)248-264
Journal / PublicationPattern Recognition
Online published21 Sept 2018
Publication statusPublished - Feb 2019


Unsupervised multi-task learning exploits the shared knowledge to improve performances by learning related tasks simultaneously. In this paper, we propose an unsupervised multi-task learning method with hierarchical data structure. It strengthens similarities between instances in the same cluster, and increases diversities of instances by utilizing instances from related clusters. Firstly, we introduce Representative Dual Features (RepDFs) that possess representative capabilities in the feature space and the sample space for each cluster concurrently. Secondly, we explore hierarchical structural similarities between clusters in related tasks from the topological perspective: 1) feature basis matrix, which learns compact representations for features in the feature space; and 2) sample refined matrix, which preserves local structures in the sample space. Thirdly, we adopt RepDFs to measure correlations between clusters and incorporate hierarchical structural similarities to conduct knowledge transfer among tasks. Experimental results on real-world data sets demonstrate the effectiveness and superiority of the proposed method over existing multi-task clustering methods.

Research Area(s)

  • hierarchical structure, Multi-task learning, structural similarity, unsupervised learning