RankGraph: Unified Heterogeneous Graph Learning for Cross-Domain Recommendation

2025-09-02

AI Summary

Cross-domain recommendation faces challenges in modeling fine-grained user-item relationships across multiple domains. To address this, we propose a unified heterogeneous graph learning framework: first, we construct a heterogeneous graph integrating cross-domain interactions; second, we design a GPU-accelerated graph neural network coupled with a contrastive learning module to enable efficient cross-domain similarity retrieval and real-time clustering; third, we introduce a novel dynamic subgraph extraction mechanism that injects pre-trained structural representations—serving as contextual tokens—into a sequential recommendation model, thereby achieving deep fusion of structural relational knowledge and sequential pattern modeling. Online A/B testing demonstrates significant improvements: +0.92% in click-through rate (CTR) and +2.82% in conversion rate (CVR), validating the effectiveness of our approach.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Cross-domain recommendation systems face the challenge of integrating fine-grained user and item relationships across various product domains. To address this, we introduce RankGraph, a scalable graph learning framework designed to serve as a core component in recommendation foundation models (FMs). By constructing and leveraging graphs composed of heterogeneous nodes and edges across multiple products, RankGraph enables the integration of complex relationships between users, posts, ads, and other entities. Our framework employs a GPU-accelerated Graph Neural Network and contrastive learning, allowing for dynamic extraction of subgraphs such as item-item and user-user graphs to support similarity-based retrieval and real-time clustering. Furthermore, RankGraph integrates graph-based pretrained representations as contextual tokens into FM sequence models, enriching them with structured relational knowledge. RankGraph has demonstrated improvements in click (+0.92%) and conversion rates (+2.82%) in online A/B tests, showcasing its effectiveness in cross-domain recommendation scenarios.

Problem

• Integrating fine-grained user and item relationships across product domains
• Leveraging heterogeneous graphs for cross-domain recommendation systems
• Enriching foundation models with structured relational knowledge from graphs

Innovation

• Heterogeneous graph learning for cross-domain integration
• GPU-accelerated GNN with contrastive learning
• Graph pretrained representations as contextual tokens