Extreme Learning Machines for Fast Training of Click-Through Rate Prediction Models

TL;DR

This paper introduces an ELM-based model with embedding layers for CTR prediction, achieving fast training and competitive accuracy on benchmark datasets, thus demonstrating ELMs' potential in high-dimensional prediction tasks.

Contribution

The paper presents a novel ELM model with embedding layers tailored for CTR prediction, addressing high dimensionality and demonstrating rapid training with competitive results.

Findings

ELM with embeddings achieves competitive F1 scores.

The proposed model trains significantly faster than state-of-the-art methods.

ELMs are effective for high-dimensional CTR prediction tasks.

Abstract

Extreme Learning Machines (ELM) provide a fast alternative to traditional gradient-based learning in neural networks, offering rapid training and robust generalization capabilities. Its theoretical basis shows its universal approximation capability. We explore the application of ELMs for the task of Click-Through Rate (CTR) prediction, which is largely unexplored by ELMs due to the high dimensionality of the problem. We introduce an ELM-based model enhanced with embedding layers to improve the performance on CTR tasks, which is a novel addition to the field. Experimental results on benchmark datasets, including Avazu and Criteo, demonstrate that our proposed ELM with embeddings achieves competitive F1 results while significantly reducing training time compared to state-of-the-art models such as Masknet. Our findings show that ELMs can be useful for CTR prediction, especially when fast training is needed.