HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation

TL;DR

The paper introduces HAKG, a hierarchy-aware knowledge gated network that models hierarchical structures and high-order collaborative signals in recommendation systems using hyperbolic space, improving performance and interpretability.

Contribution

It proposes a novel hyperbolic aggregation scheme and dual embedding design to better capture hierarchical relations and collaborative signals in recommendation models.

Findings

Significant performance improvements over state-of-the-art methods.

Effective modeling of hierarchical structures in data.

Meaningful insights into data hierarchies from hyperbolic embeddings.

Abstract

Knowledge graph (KG) plays an increasingly important role to improve the recommendation performance and interpretability. A recent technical trend is to design end-to-end models based on information propagation schemes. However, existing propagation-based methods fail to (1) model the underlying hierarchical structures and relations, and (2) capture the high-order collaborative signals of items for learning high-quality user and item representations. In this paper, we propose a new model, called Hierarchy-Aware Knowledge Gated Network (HAKG), to tackle the aforementioned problems. Technically, we model users and items (that are captured by a user-item graph), as well as entities and relations (that are captured in a KG) in hyperbolic space, and design a hyperbolic aggregation scheme to gather relational contexts over KG. Meanwhile, we introduce a novel angle constraint to preserve characteristics of items in the embedding space. Furthermore, we propose a dual item embeddings design to represent and propagate collaborative signals and knowledge associations separately, and leverage the gated aggregation to distill discriminative information for better capturing user behavior patterns. Experimental results on three benchmark datasets show that, HAKG achieves significant improvement over the state-of-the-art methods like CKAN, Hyper-Know, and KGIN. Further analyses on the learned hyperbolic embeddings confirm that HAKG offers meaningful insights into the hierarchies of data.