Flexible Clustered Multi-Task Learning by Learning Representative Tasks

By Qiang Zhou, Qi Zhao. 2016

77 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computational Mechanics, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xing Xie
2. Qiang Yang
3. Hongwei Wang
4. Wenjie Li
5. Miao Zhao
6. Fuzheng Zhang
7. Yu Zhang
8. Minyi Guo

In Computational Mechanics

1. Qiang Yang
2. Yu Zhang
3. Xing Xie

In Electrical and Electronic Engineering

1. Yu Zhang
2. Qiang Yang
3. Xing Xie
4. Dongrui Wu
5. Vladlen Koltun
6. Ozan Sener

Citations in the corpus

• A Survey on Multi-Task Learning (2017, methodology): “Zhou and Zhao [65] aim to cluster tasks by identifying representative tasks which are a subset of the givenm tasks.”
• Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation (2019, methodology): “In general, MTL algorithms can be classified into several categories, including feature learning approach [34, 41], low-rank approach [7, 16], task clustering approach [47], task relation learning approach [12], and decomposition approach [6].”