Flexible Clustered Multi-Task Learning by Learning Representative Tasks

Qiang Zhou, Qi Zhao

Research output: Contribution to journalArticlepeer-review

27 Scopus citations

Abstract

Multi-task learning (MTL) methods have shown promising performance by learning multiple relevant tasks simultaneously, which exploits to share useful information across relevant tasks. Among various MTL methods, clustered multi-task learning (CMTL) assumes that all tasks can be clustered into groups and attempts to learn the underlying cluster structure from the training data. In this paper, we present a new approach for CMTL, called flexible clustered multi-task (FCMTL), in which the cluster structure is learned by identifying representative tasks. The new approach allows an arbitrary task to be described by multiple representative tasks, effectively soft-assigning a task to multiple clusters with different weights. Unlike existing counterpart, the proposed approach is more flexible in that (a) it does not require clusters to be disjoint, (b) tasks within one particular cluster do not have to share information to the same extent, and (c) the number of clusters is automatically inferred from data. Computationally, the proposed approach is formulated as a row-sparsity pursuit problem. We validate the proposed FCMTL on both synthetic and real-world data sets, and empirical results demonstrate that it outperforms many existing MTL methods.

Original languageEnglish (US)
Article number7150415
Pages (from-to)266-278
Number of pages13
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume38
Issue number2
DOIs
StatePublished - Feb 1 2016

Keywords

  • Clustered Multi-Task Learning
  • Group Sparsity
  • Representative Task

Fingerprint Dive into the research topics of 'Flexible Clustered Multi-Task Learning by Learning Representative Tasks'. Together they form a unique fingerprint.

Cite this