# Hierarchical Attentive Knowledge Graph Embedding for Personalized Recommendation

arXiv: https://arxiv.org/abs/1910.08288 · HTML: https://mlsanity.com/paper/1910.08288/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2019.

## Built on by (most cited first, 9 of 9)

- [Conditional Attention Networks for Distilling Knowledge Graphs in Recommendation](https://mlsanity.com/paper/2111.02100/) (2021)
- [Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation](https://mlsanity.com/paper/2106.03415/) (2021)
- [GDDA: Semantic OOD Detection on Graphs under Covariate Shift via Score-Based Diffusion Models](https://mlsanity.com/paper/2410.17526/) (2024)
- [Augmenting the User-Item Graph with Textual Similarity Models](https://mlsanity.com/paper/2109.09358/) (2021)
- [SSTKG: Simple Spatio-Temporal Knowledge Graph for Intepretable and Versatile Dynamic Information Embedding](https://mlsanity.com/paper/2402.12132/) (2024)
- [Stability of Explainable Recommendation](https://mlsanity.com/paper/2405.01849/) (2024)
- [Robust Explainable Recommendation](https://mlsanity.com/paper/2405.01855/) (2024)
- [OKRA: an Explainable, Heterogeneous, Multi-Stakeholder Job Recommender System](https://mlsanity.com/paper/2504.07108/) (2025)
- [Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation](https://mlsanity.com/paper/2512.13120/) (2025)

## Abstract (arXiv)

Knowledge graphs (KGs) have proven to be effective for high-quality recommendation, where the connectivities between users and items provide rich and complementary information to user-item interactions. Most existing methods, however, are insufficient to exploit the KGs for capturing user preferences, as they either represent the user-item connectivities via paths with limited expressiveness or implicitly model them by propagating information over the entire KG with inevitable noise. In this paper, we design a novel hierarchical attentive knowledge graph embedding (HAKG) framework to exploit the KGs for effective recommendation. Specifically, HAKG first extracts the expressive subgraphs that link user-item pairs to characterize their connectivities, which accommodate both the semantics and topology of KGs. The subgraphs are then encoded via a hierarchical attentive subgraph encoding to generate effective subgraph embeddings for enhanced user preference prediction. Extensive experiments show the superiority of HAKG against state-of-the-art recommendation methods, as well as its potential in alleviating the data sparsity issue.