A Survey on Knowledge Graph-Based Recommender Systems

Guo, Qingyu; Zhuang, Fuzhen; Qin, Chuan; Zhu, Hengshu; Xie, Xing; Xiong, Hui; He, Qing

doi:10.48550/arxiv.2003.00911

Cited by 7 publications

(5 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A more comprehensive review for KG-based recommendation can refer to [8]. The proposed UGRec method in this paper falls into the first approach, and it adopts different strategies to model both directed knowledge relations and the undirected item-item co-occurrence relations for entity embedding learning in a unified graph-based model.…”

Section: Related Workmentioning

confidence: 99%

UGRec: Modeling Directed and Undirected Relations for Recommendation

Zhao

Cheng

Zhu

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Recommender systems, which merely leverage user-item interactions for user preference prediction (such as the collaborative filtering-based ones), often face dramatic performance degradation when the interactions of users or items are insufficient. In recent years, various types of side information have been explored to alleviate this problem. Among them, knowledge graph (KG) has attracted extensive research interests as it can encode users/items and their associated attributes in the graph structure to preserve the relation information. In contrast, less attention has been paid to the item-item co-occurrence information (i.e., co-view), which contains rich item-item similarity information. It provides information from a perspective different from the user/item-attribute graph and is also valuable for the CF recommendation models. In this work, we make an effort to study the potential of integrating both types of side information (i.e., KG and item-item co-occurrence data) for recommendation. To achieve the goal, we propose a unified graph-based recommendation model (UGRec), which integrates the traditional directed relations in KG and the undirected itemitem co-occurrence relations simultaneously. In particular, for a directed relation, we transform the head and tail entities into the corresponding relation space to model their relation; and for an undirected co-occurrence relation, we project head and tail entities into a unique hyperplane in the entity space to minimize their distance. In addition, a head-tail relation-aware attentive mechanism is designed for fine-grained relation modeling. Extensive experiments have been conducted on several publicly accessible datasets to evaluate the proposed model. Results show that our model outperforms several previous state-of-the-art methods and demonstrate the effectiveness of our UGRec model.

show abstract

Section: Related Workmentioning

confidence: 99%

UGRec: Modeling Directed and Undirected Relations for Recommendation

Zhao

Cheng

Zhu

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

show abstract

“…Despite the rich information in KG, utilizing KG in RS is rather challenging due to its complex graph structure, i.e., multi-type entities and multi-type relations [13]. Previous works preprocess KG by knowledge graph embedding methods to learn the embeddings of entities and relations, such as [8,59,75,79] or design meta-paths to aggregate the neighbor information [47,50,64,74].…”

Section: Knowledge Graph Enhancedmentioning

confidence: 99%

Graph Neural Networks in Recommender Systems: A Survey

Wu¹,

Sun²,

Zhang³

et al. 2020

Preprint

View full text Add to dashboard Cite

With the explosive growth of online information, recommender systems play a key role to alleviate such information overload. Due to the important application value of recommender system, there have always been emerging works in this field. In recent years, graph neural network (GNN) techniques have gained considerable interests which can naturally integrate node information and topological structure. Owing to the outperformance of GNN in learning on graph data, GNN methods have been widely applied in many fields. In recommender systems, the main challenge is to learn the efficient user/item embeddings from their interactions and side information if available. Since most of the information essentially has graph structure and GNNs have superiority in representation learning, the field of utilizing graph neural network in recommender systems is flourishing. This article aims to provide a comprehensive review of recent research efforts on graph neural network based recommender systems. Specifically, we provide a taxonomy of graph neural network based recommendation models and state new perspectives pertaining to the development of this field.

show abstract

“…Different from bipartite graphs, the other heterographs exploited the side-information into the user-item interaction graph to enhance the recommendation ability. The researches on this domain mainly focus on the usage of knowledge graph (KG) [19]. Some works, such as CKE [20], DKN [21], RKGE [22], and KPRN [23], only exploited the knowledge of KG to enrich the representations [20,21] or only leverage the connectivity patterns of the entity in KG to help the recommendation [22,23].…”

Section: Graph-based Recommendationmentioning

confidence: 99%