A Convex Formulation for Learning Task Relationships in Multi-Task Learning

TL;DR

This paper introduces a convex regularization framework for multi-task learning that models positive and negative task relationships, including outliers, improving generalization across tasks.

Contribution

It proposes a novel convex formulation called MTRL that captures diverse task relationships and extends to both symmetric and asymmetric multi-task learning settings.

Findings

MTRL effectively models positive and negative task correlations.

The convex formulation enables efficient alternating optimization.

Experiments show MTRL outperforms existing methods on benchmark datasets.

Abstract

Multi-task learning is a learning paradigm which seeks to improve the generalization performance of a learning task with the help of some other related tasks. In this paper, we propose a regularization formulation for learning the relationships between tasks in multi-task learning. This formulation can be viewed as a novel generalization of the regularization framework for single-task learning. Besides modeling positive task correlation, our method, called multi-task relationship learning (MTRL), can also describe negative task correlation and identify outlier tasks based on the same underlying principle. Under this regularization framework, the objective function of MTRL is convex. For efficiency, we use an alternating method to learn the optimal model parameters for each task as well as the relationships between tasks. We study MTRL in the symmetric multi-task learning setting and then generalize it to the asymmetric setting as well. We also study the relationships between MTRL and some existing multi-task learning methods. Experiments conducted on a toy problem as well as several benchmark data sets demonstrate the effectiveness of MTRL.