Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta review

Richa Upadhyay, Ronald Phlypo, Rajkumar Saini, Marcus Liwicki

TL;DR

A generic task-agnostic and model-agnostic learning network – an ensemble of meta-learning, transfer learning, and multi-task learning, termed Multi-modal Multi-task Meta Transfer Learning is hypothesized.

Abstract

Integrating knowledge across different domains is an essential feature of human learning. Learning paradigms such as transfer learning, meta-learning, and multi-task learning reflect the human learning process by exploiting the prior knowledge for new tasks, encouraging faster learning and good generalization for new tasks. This article gives a detailed view of these learning paradigms and their comparative analysis. The weakness of one learning algorithm turns out to be a strength of another, and thus, merging them is a prevalent trait in the literature. Numerous research papers focus on each of these learning paradigms separately and provide a comprehensive overview of them. However, this article reviews research studies that combine (two of) these learning algorithms. This survey describes how these techniques are combined to solve problems in many different fields of research, including computer vision, natural language processing, hyper-spectral imaging, and many more, in a supervised setting only. Based on the knowledge accumulated from the literature, we hypothesize a generic task-agnostic and model-agnostic learning network - an ensemble of meta-learning, transfer learning, and multi-task learning, termed Multi-modal Multi-task Meta Transfer Learning. We also present some open research questions, limitations, and future research directions for this proposed network. The aim of this article is to spark interest among scholars in effectively merging existing learning algorithms with the intention of advancing research in this field. Instead of presenting experimental results, we invite readers to explore and contemplate techniques for merging algorithms while navigating through their limitations.

Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta review

TL;DR

A generic task-agnostic and model-agnostic learning network – an ensemble of meta-learning, transfer learning, and multi-task learning, termed Multi-modal Multi-task Meta Transfer Learning is hypothesized.

Abstract

Integrating knowledge across different domains is an essential feature of human learning. Learning paradigms such as transfer learning, meta-learning, and multi-task learning reflect the human learning process by exploiting the prior knowledge for new tasks, encouraging faster learning and good generalization for new tasks. This article gives a detailed view of these learning paradigms and their comparative analysis. The weakness of one learning algorithm turns out to be a strength of another, and thus, merging them is a prevalent trait in the literature. Numerous research papers focus on each of these learning paradigms separately and provide a comprehensive overview of them. However, this article reviews research studies that combine (two of) these learning algorithms. This survey describes how these techniques are combined to solve problems in many different fields of research, including computer vision, natural language processing, hyper-spectral imaging, and many more, in a supervised setting only. Based on the knowledge accumulated from the literature, we hypothesize a generic task-agnostic and model-agnostic learning network - an ensemble of meta-learning, transfer learning, and multi-task learning, termed Multi-modal Multi-task Meta Transfer Learning. We also present some open research questions, limitations, and future research directions for this proposed network. The aim of this article is to spark interest among scholars in effectively merging existing learning algorithms with the intention of advancing research in this field. Instead of presenting experimental results, we invite readers to explore and contemplate techniques for merging algorithms while navigating through their limitations.
Paper Structure (26 sections, 5 equations, 7 figures, 2 tables)

This paper contains 26 sections, 5 equations, 7 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Knowledge transfer in machine learning algorithms
  3. Types of knowledge transfer
  4. What is a Task?
  5. Scope of this work
  6. Contribution
  7. Structure
  8. Learning paradigms
  9. Definitions and Notations
  10. Supervised Learning
  11. Transfer Learning
  12. Multi-task Learning
  13. meta-learning
  14. Comparisons
  15. Transfer learning and MTL
  16. ...and 11 more sections

Figures (7)

  • Figure 1: The figure shows two types of transfer learning from the source to the target task. The images are taken from the ImageNet dataset 5206848.
  • Figure 2: Illustration of PAD-Net architecture proposed by Xu2018PADNetMG, with four primary tasks: monocular depth estimation, surface normal estimation, edge detection, and semantic segmentation. Outputs are integrated to predict two output tasks: depth estimation and scene parsing. Here, Loss 1 - Loss 4 represent optimization losses for various tasks. All images in the figure are from the Taskonomy dataset zamir2018taskonomy.
  • Figure 3: An example of meta-learning illustrating 4 shot 2 class image classification.
  • Figure 4: A comparative representation of how tasks are introduced in the learning paradigms
  • Figure 5: Illustration of the integration of transfer learning and MTL Ye_2018.
  • ...and 2 more figures