Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation


  • Lianghao Xia South China University of Technology
  • Chao Huang JD Finance America Corporation
  • Yong Xu South China University of Technology Communication and Computer Network Laboratory of Guangdong Peng Cheng Laboratory
  • Peng Dai JD Finance America Corporation
  • Xiyue Zhang South China University of Technology
  • Hongsheng Yang JD Finance America Corporation
  • Jian Pei Simon Fraser University
  • Liefeng Bo JD Finance America Corporation



Recommender Systems & Collaborative Filtering, Graph Mining, Social Network Analysis & Community


Accurate user and item embedding learning is crucial for modern recommender systems. However, most existing recommendation techniques have thus far focused on modeling users' preferences over singular type of user-item interactions. Many practical recommendation scenarios involve multi-typed user interactive behaviors (e.g., page view, add-to-favorite and purchase), which presents unique challenges that cannot be handled by current recommendation solutions. In particular: i) complex inter-dependencies across different types of user behaviors; ii) the incorporation of knowledge-aware item relations into the multi-behavior recommendation framework; iii) dynamic characteristics of multi-typed user-item interactions. To tackle these challenges, this work proposes a Knowledge-Enhanced Hierarchical Graph Transformer Network (KHGT), to investigate multi-typed interactive patterns between users and items in recommender systems. Specifically, KHGT is build upon a graph-structured neural architecture to i) capture type-specific behavior semantics; ii) explicitly discriminate which types of user-item interactions are more important in assisting the forecasting task on the target behavior. Additionally, we further integrate the multi-modal graph attention layer with temporal encoding strategy, to empower the learned embeddings be reflective of both dedicated multiplex user-item and item-item collaborative relations, as well as the underlying interaction dynamics. Extensive experiments conducted on three real-world datasets show that KHGT consistently outperforms many state-of-the-art recommendation methods across various evaluation settings. Our implementation is available in




How to Cite

Xia, L., Huang, C., Xu, Y., Dai, P., Zhang, X., Yang, H., Pei, J., & Bo, L. (2021). Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4486-4493.



AAAI Technical Track on Data Mining and Knowledge Management