Feature embedding in click-through rate prediction

TL;DR

This paper introduces five novel feature embedding modules to enhance click-through rate prediction models, demonstrating improved accuracy with minimal additional training time.

Contribution

The paper proposes five new feature embedding modules that can be integrated into existing CTR prediction models to boost performance.

Findings

Embedding modules significantly improve predictive accuracy.

Enhanced models maintain efficient training times.

Modules are effective across multiple baseline models.

Abstract

We tackle the challenge of feature embedding for the purposes of improving the click-through rate prediction process. We select three models: logistic regression, factorization machines and deep factorization machines, as our baselines and propose five different feature embedding modules: embedding scaling, FM embedding, embedding encoding, NN embedding and the embedding reweighting module. The embedding modules act as a way to improve baseline model feature embeddings and are trained alongside the rest of the model parameters in an end-to-end manner. Each module is individually added to a baseline model to obtain a new augmented model. We test the predictive performance of our augmented models on a publicly accessible dataset used for benchmarking click-through rate prediction models. Our results show that several proposed embedding modules provide an important increase in predictive performance without a drastic increase in training time.