Task Grouping for Automated Multi-Task Machine Learning via Task Affinity Prediction

TL;DR

This paper introduces an automated method for task grouping in multi-task learning, using a predictor of task affinity to improve grouping decisions and enhance model performance across benchmark datasets.

Contribution

The paper presents a novel predictor for task affinity and a search algorithm that automates task grouping, outperforming existing methods in multi-task learning scenarios.

Findings

Predictor accurately estimates task affinity for MTL.

Automated grouping yields better performance than manual or baseline methods.

Method reduces the number of MTL trainings needed during task grouping.

Abstract

When a number of similar tasks have to be learned simultaneously, multi-task learning (MTL) models can attain significantly higher accuracy than single-task learning (STL) models. However, the advantage of MTL depends on various factors, such as the similarity of the tasks, the sizes of the datasets, and so on; in fact, some tasks might not benefit from MTL and may even incur a loss of accuracy compared to STL. Hence, the question arises: which tasks should be learned together? Domain experts can attempt to group tasks together following intuition, experience, and best practices, but manual grouping can be labor-intensive and far from optimal. In this paper, we propose a novel automated approach for task grouping. First, we study the affinity of tasks for MTL using four benchmark datasets that have been used extensively in the MTL literature, focusing on neural network-based MTL models. We identify inherent task features and STL characteristics that can help us to predict whether a group of tasks should be learned together using MTL or if they should be learned independently using STL. Building on this predictor, we introduce a randomized search algorithm, which employs the predictor to minimize the number of MTL trainings performed during the search for task groups. We demonstrate on the four benchmark datasets that our predictor-driven search approach can find better task groupings than existing baseline approaches.