Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction

TL;DR

This paper introduces PCF-GNN, a pre-trained graph neural network model that explicitly learns semantic cross features for CTR prediction, outperforming implicit methods in accuracy and memory efficiency.

Contribution

The paper presents the first GNN-based pre-trained model for explicit semantic cross feature learning in CTR prediction, addressing generalization and memory challenges.

Findings

PCF-GNN outperforms existing methods in accuracy on public and industrial datasets.

PCF-GNN demonstrates superior memory efficiency compared to traditional explicit methods.

Extensive experiments validate the effectiveness of PCF-GNN across various tasks.

Abstract

Cross features play an important role in click-through rate (CTR) prediction. Most of the existing methods adopt a DNN-based model to capture the cross features in an implicit manner. These implicit methods may lead to a sub-optimized performance due to the limitation in explicit semantic modeling. Although traditional statistical explicit semantic cross features can address the problem in these implicit methods, it still suffers from some challenges, including lack of generalization and expensive memory cost. Few works focus on tackling these challenges. In this paper, we take the first step in learning the explicit semantic cross features and propose Pre-trained Cross Feature learning Graph Neural Networks (PCF-GNN), a GNN based pre-trained model aiming at generating cross features in an explicit fashion. Extensive experiments are conducted on both public and industrial datasets, where PCF-GNN shows competence in both performance and memory-efficiency in various tasks.