Causality-based CTR Prediction using Graph Neural Networks

TL;DR

This paper introduces Causal-GNN, a graph neural network model for CTR prediction that incorporates causal relationships among features, users, and ads, leading to improved performance on out-of-distribution data.

Contribution

It develops a causality-based GNN framework with a novel GraphFwFM method for high-order feature representation, addressing limitations of previous models that ignore causal relationships.

Findings

Causal-GNN outperforms existing models in AUC and Logloss on public datasets.

GraphFwFM effectively captures high-order causal feature interactions.

The model demonstrates robustness on out-of-distribution data.

Abstract

As a prevalent problem in online advertising, CTR prediction has attracted plentiful attention from both academia and industry. Recent studies have been reported to establish CTR prediction models in the graph neural networks (GNNs) framework. However, most of GNNs-based models handle feature interactions in a complete graph, while ignoring causal relationships among features, which results in a huge drop in the performance on out-of-distribution data. This paper is dedicated to developing a causality-based CTR prediction model in the GNNs framework (Causal-GNN) integrating representations of feature graph, user graph and ad graph in the context of online advertising. In our model, a structured representation learning method (GraphFwFM) is designed to capture high-order representations on feature graph based on causal discovery among field features in gated graph neural networks (GGNNs), and GraphSAGE is employed to obtain graph representations of users and ads. Experiments conducted on three public datasets demonstrate the superiority of Causal-GNN in AUC and Logloss and the effectiveness of GraphFwFM in capturing high-order representations on causal feature graph.