RankGraph: Unified Heterogeneous Graph Learning for Cross-Domain Recommendation
This addresses the problem of enhancing recommendation accuracy and performance for users and businesses in cross-domain scenarios, representing an incremental advancement by combining existing techniques like GNNs and contrastive learning in a novel framework.
The paper tackles the challenge of integrating fine-grained user and item relationships across product domains in cross-domain recommendation systems by introducing RankGraph, a scalable graph learning framework that improved click rates by +0.92% and conversion rates by +2.82% in online A/B tests.
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.