TextBridgeGNN: Pre-training Graph Neural Network for Cross-Domain Recommendation via Text-Guided Transfer

2025-11-25

arXiv.org

AI Summary

This work addresses the challenge of knowledge transfer in ID-based graph recommendation models under cross-domain settings, where isolated ID spaces and heterogeneous graph structures hinder effective migration. To overcome this, we propose TextBridgeGNN, a novel framework that leverages textual semantics as a bridge to enable cross-domain knowledge transfer. Our approach employs a hierarchical graph neural network to jointly learn both domain-general and domain-specific representations during pre-training. During fine-tuning, a similarity-based transfer mechanism initializes target-domain ID embeddings, facilitating effective propagation of collaborative signals across domains. Notably, TextBridgeGNN requires neither large language model fine-tuning nor real-time inference, yet consistently outperforms existing methods across cross-domain, multi-domain, and zero-shot scenarios, demonstrating strong effectiveness and generalization capability.

Abstract

Graph-based recommendation has achieved great success in recent years. The classical graph recommendation model utilizes ID embedding to store essential collaborative information. However, this ID-based paradigm faces challenges in transferring to a new domain, making it hard to build a pre-trained graph recommendation model. This phenomenon primarily stems from two inherent challenges: (1) the non-transferability of ID embeddings due to isolated domain-specific ID spaces, and (2) structural incompatibility between heterogeneous interaction graphs across domains. To address these issues, we propose TextBridgeGNN, a pre-training and fine-tuning framework that can effectively transfer knowledge from a pre-trained GNN to downstream tasks. We believe the key lies in how to build the relationship between domains. Specifically, TextBridgeGNN uses text as a semantic bridge to connect domains through multi-level graph propagation. During the pre-training stage, textual information is utilized to break the data islands formed by multiple domains, and hierarchical GNNs are designed to learn both domain-specific and domain-global knowledge with text features, ensuring the retention of collaborative signals and the enhancement of semantics. During the fine-tuning stage, a similarity transfer mechanism is proposed. This mechanism initializes ID embeddings in the target domain by transferring from semantically related nodes, successfully transferring the ID embeddings and graph pattern. Experiments demonstrate that TextBridgeGNN outperforms existing methods in cross-domain, multi-domain, and training-free settings, highlighting its ability to integrate Pre-trained Language Model (PLM)-driven semantics with graph-based collaborative filtering without costly language model fine-tuning or real-time inference overhead.

Problem

• cross-domain recommendation
• ID embedding transferability
• structural incompatibility
• heterogeneous interaction graphs
• graph neural network

Innovation

• cross-domain recommendation
• graph neural network
• text-guided transfer
• pre-training
• semantic bridge