An Overview of Multi-Task Learning in Deep Neural Networks

TL;DR

This paper provides a comprehensive overview of multi-task learning in deep neural networks, covering methods, literature, recent advances, and practical guidelines for application.

Contribution

It offers a detailed summary of MTL techniques, recent developments, and practical advice for practitioners, filling a gap in accessible, consolidated knowledge.

Findings

Two main MTL methods in deep learning are identified.

Recent advances improve MTL effectiveness and applicability.

Guidelines help practitioners select suitable auxiliary tasks.

Abstract

Multi-task learning (MTL) has led to successes in many applications of machine learning, from natural language processing and speech recognition to computer vision and drug discovery. This article aims to give a general overview of MTL, particularly in deep neural networks. It introduces the two most common methods for MTL in Deep Learning, gives an overview of the literature, and discusses recent advances. In particular, it seeks to help ML practitioners apply MTL by shedding light on how MTL works and providing guidelines for choosing appropriate auxiliary tasks.