Feature Representation Learning for Click-through Rate Prediction: A Review and New Perspectives

TL;DR

This paper reviews the current state of feature representation learning in click-through rate prediction, categorizing methods and discussing future research directions to enhance model performance.

Contribution

It provides a comprehensive taxonomy and analysis of existing feature representation methods in CTR prediction, highlighting new perspectives for future research.

Findings

Summarizes various feature representation techniques in CTR models.

Identifies key challenges and future directions in the field.

Provides a structured taxonomy for understanding current methods.

Abstract

Representation learning has been a critical topic in machine learning. In Click-through Rate Prediction, most features are represented as embedding vectors and learned simultaneously with other parameters in the model. With the development of CTR models, feature representation learning has become a trending topic and has been extensively studied by both industrial and academic researchers in recent years. This survey aims at summarizing the feature representation learning in a broader picture and pave the way for future research. To achieve such a goal, we first present a taxonomy of current research methods on feature representation learning following two main issues: (i) which feature to represent and (ii) how to represent these features. Then we give a detailed description of each method regarding these two issues. Finally, the review concludes with a discussion on the future directions of this field.