Contrastive Representation Learning: A Framework and Review

TL;DR

This paper reviews the development of contrastive learning across multiple fields, introduces a unifying framework and taxonomy, and discusses its applications, biases, challenges, and future directions.

Contribution

It provides a comprehensive literature review, a general contrastive learning framework, and a taxonomy to unify and clarify various contrastive learning methods.

Findings

Contrastive learning has diverse applications across vision, language, and audio.

A unified framework helps clarify the components and biases of contrastive learning.

Identifies challenges and promising future research directions in contrastive learning.

Abstract

Contrastive Learning has recently received interest due to its success in self-supervised representation learning in the computer vision domain. However, the origins of Contrastive Learning date as far back as the 1990s and its development has spanned across many fields and domains including Metric Learning and natural language processing. In this paper we provide a comprehensive literature review and we propose a general Contrastive Representation Learning framework that simplifies and unifies many different contrastive learning methods. We also provide a taxonomy for each of the components of contrastive learning in order to summarise it and distinguish it from other forms of machine learning. We then discuss the inductive biases which are present in any contrastive learning system and we analyse our framework under different views from various sub-fields of Machine Learning. Examples of how contrastive learning has been applied in computer vision, natural language processing, audio processing, and others, as well as in Reinforcement Learning are also presented. Finally, we discuss the challenges and some of the most promising future research directions ahead.