GraphLLM4CTR: Large Language Model-enhanced Graph Neural Networks for Click-through Rate Prediction in Recommender Systems
Open Access
- 20 October 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (9) , 1-41
Abstract
Click-through rate (CTR) prediction is a crucial task to estimate the probability that users will click on items in online platforms. Recently, researchers have incorporated semantics derived from large language models (LLMs) into representations of users and items in a graph neural network (GNN) framework to facilitate CTR prediction. However, existing hybrid GNN-LLM models predominantly treat GNNs and LLMs as two independent components and suffer from ineffective modality alignment between graph and textual representations. To address these issues, we propose LLMs-enhanced GNNs for CTR prediction (GraphLLM4CTR), where LLMs coordinate message passing in GNNs by infusing layer-wise semantics into message updates and graph representation learning. Specifically, we design a multi-view contrastive alignment (MVCA) method to transform graph and prompt-based embeddings into modality-aware representations and achieve modality alignment through intra-view and inter-view contrastive learning. Moreover, we propose an LLMs-based message coordinator (LBMC) that projects graph representations into an aligned latent space and incorporates LLMs with learnable adapters to regulate semantic-injected graph representation learning. Subsequently, we present a hybrid-expert mechanism with gating networks to adaptively aggregate representations for CTR prediction. Experiments conducted on three public datasets (i.e., MovieLens-1M, BookCrossing, and Amazon-Sports) demonstrate the superiority of GraphLLM4CTR over state-of-the-art baselines in terms of AUC and Logloss, and validate the adaptability of MVCA to topological properties and of LBMC to text qualities, and the dynamic balance of the hybrid-expert mechanism. Finally, we conduct an analysis of space and time complexity and computational efficiency of GraphLLM4CTR during training and inference stages, which indicates that GraphLLM4CTR can achieve the optimal AUC-latency tradeoff and linear scalability with the number of nodes and edges in constructed graphs.Keywords
Funding Information
- NSFC (72171093)
This publication has 75 references indexed in Scilit:
- A survey on knowledge graph-based click-through rate predictionExpert Systems with Applications, 2025
- GraphFM: Graph Factorization Machines for Feature Interaction ModellingMachine Intelligence Research, 2025
- FinalGNN: A dual feature graph enhanced model for CTR predictionNeurocomputing, 2024
- Causality-based CTR prediction using graph neural networksInformation Processing & Management, 2022
- Time-varying effects of search engine advertising on sales–An empirical investigation in E-commerceDecision Support Systems, 2022
- Click-through rate prediction in online advertising: A literature reviewInformation Processing & Management, 2022
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- Modeling Relational Data with Graph Convolutional Networks2018
- Product-Based Neural Networks for User Response Prediction2016
- Factorization Machines2010