Does Negative Sampling Matter? A Review with Insights into its Theory and Applications

TL;DR

This paper reviews the importance, theoretical foundations, and diverse applications of negative sampling across multiple fields, proposing a unified framework and categorization of existing methods.

Contribution

It introduces a comprehensive framework for negative sampling, categorizes existing methods, and provides insights into its applications and future research directions.

Findings

Negative sampling is crucial across various machine learning domains.

Current methods can be categorized into five distinct types.

The paper highlights open problems and future directions in negative sampling.

Abstract

Negative sampling has swiftly risen to prominence as a focal point of research, with wide-ranging applications spanning machine learning, computer vision, natural language processing, data mining, and recommender systems. This growing interest raises several critical questions: Does negative sampling really matter? Is there a general framework that can incorporate all existing negative sampling methods? In what fields is it applied? Addressing these questions, we propose a general framework that leverages negative sampling. Delving into the history of negative sampling, we trace the development of negative sampling through five evolutionary paths. We dissect and categorize the strategies used to select negative sample candidates, detailing global, local, mini-batch, hop, and memory-based approaches. Our review categorizes current negative sampling methods into five types: static, hard, GAN-based, Auxiliary-based, and In-batch methods, providing a clear structure for understanding negative sampling. Beyond detailed categorization, we highlight the application of negative sampling in various areas, offering insights into its practical benefits. Finally, we briefly discuss open problems and future directions for negative sampling.