Causality-based CTR prediction using graph neural networks. Issue 1 (January 2023)

• Record Type: Journal Article
• Authors: Zhai, Panyu; Yang, Yanwu; Zhang, Chunjie
• Is Part Of: Information processing & management. Volume 60:Issue 1(2023)
• Publication Date: 2023-01
• Subjects: CTR prediction -- Graph neural networks -- Feature interactions -- Causal inference -- Online advertising; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2022.103137
• Languages: English
• ISSNs: 0306-4573

Abstract

Highlights: Propose a causality-based CTR prediction model in the GNNs framework (Causal-GNN) integrating representations of feature graph, user graph and ad graph. Design a structured representation learning method (GraphFwFM) to capture high-order representations on feature graph based on causal inference. Conduct experiments on three public datasets to show the superiority of Causal-GNN by comparing with several state-of-the-art baselines. 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.