Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences

By Yixin Cao, Xiang Wang, Xiangnan He, Zikun Hu, Tat-seng Chua. The Web Conference, 2019

695 citations recorded by the source corpus.

Incorporating knowledge graph (KG) into recommender system is promising in improving the recommendation accuracy and explainability. However, existing methods largely assume that a KG is complete and simply transfer the ”knowledge” in KG at the shallow level of entity raw data or embeddings. This may lead to suboptimal performance, since a practical KG can hardly be complete, and it is common that a KG has missing facts, relations, and entities. Thus, we argue that it is crucial to consider the incomplete nature of KG when incorporating it into recommender system. In this paper, we jointly learn the model of recommendation and knowledge graph completion. Distinct from previous KG-based recommendation methods, we transfer the relation information in KG, so as to understand the reasons that a user likes an item. As an example, if a user has watched several movies directed by (relation) the same person (entity), we can infer that the director relation plays a critical role when the user makes the decision, thus help to understand the user's preference at a finer granularity. Technically, we contribute a new translation-based recommendation model, which specially accounts for various preferences in translating a user to an item, and then jointly train it with a KG completion model by combining several transfer schemes. Extensive experiments on two benchmark datasets show that our method outperforms state-of-the-art KG-based recommendation methods. Further analysis verifies the positive effect of joint training on both tasks of recommendation and KG completion, and the advantage of our model in understanding user preference. We publish our project at https://github.com/TaoMiner/joint-kg-recommender.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/2335a95bfed617953675b5227cc881707746f53b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Yongfeng Zhang
5. Xu Chen
6. Meng Wang
7. Liqiang Nie
8. Fuli Feng

In Information Systems

1. Xiangnan He
2. Xiang Wang
3. Tat-seng Chua
4. Yongfeng Zhang
5. Xu Chen
6. Meng Wang
7. Fuli Feng
8. Liqiang Nie

Citations in the corpus

• MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video (2019, methodology): “Due to the success of CF method in recommendation systems, early multi-modal recommendation algorithms mainly based on CF models [6, 18, 38–40].”
• A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, background): “efforts for KG enhanced recommendation can be roughly categorized into three categories: path-basedmodels [168], [174], [175], [176], [177], regularization-based models [132], [169],”
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms (2020, neutral): “KTUP [6] WWW 2019 MovieLens, DBbook2014”
• Neural Graph Collaborative Filtering (2019, methodology): “Following mainstream recommender models [1, 14, 26], we describe a user u (an item i) with an embedding vector eu ∈ Rd (ei ∈ Rd ), where d denotes the embedding size.”
• Learning Intents behind Interactions with Knowledge Graph for Recommendation (2021, methodology): “GNN-based Methods [17, 38, 39, 41, 47] are founded upon the information aggregation mechanism of graph neural networks (GNNs) [13, 14, 19, 34, 42].”
• Self-supervised Graph Learning for Recommendation (2020, background): “Recently, Knowledge Graph (KG) is also unified with the user-item graph, which enables considering the detailed types of linkage between items [4, 43, 45].”
• Multi-Channel Graph Neural Network for Entity Alignment (2019, background): “Merging different KGs into a unified one has at-tracted much attention since it shall benefit many Knowledge-driven applications, such as information extraction (Cao et al., 2017a, 2018b), question answering (Zhang et al., 2015) and recommendation (Cao et al., 2019).”
• A Survey on Application of Knowledge Graph (2020, background): “Cao et al. [30] notice it is very common that a KG has missing entities, relations, and facts.”
• Personalized Fashion Recommendation with Visual Explanations based on Multimodal Attention Network: Towards Visually Explainable Recommendation (2019, background): “KTUP [4] studied how to mutually enhance the tasks of Top-N recommendation and knowledge graph completion by learning a joint model.”
• Knowledge Graph Contrastive Learning for Recommendation (2022, background): “Particularly, some studies [3, 51] bridge the knowledge graph learning with user-item interaction modeling, through adopting the transition-based entity embedding schemes ( e.g., , TransE [2], TransR [19]) to generate prior item embeddings.”
• KGAT: Knowledge Graph Attention Network for Recommendation (2019, methodology): “We organize the side information in the form of knowledge graph G2, which is a directed graph composed of subject-property-object triple facts [5].”
• A Survey on Knowledge Graph-Based Recommender Systems (2020, methodology): “[2], [14], [44], [45], [66], [70], [81], [83], [87], [92], [93], [95], [96] MovieLens-20M [44], [86], [88], [89], [91] museums, parks, cities, etc.) to users based on their historical check-in data.”
• Explainable Interaction-driven User Modeling over Knowledge Graph for Sequential Recommendation (2019, methodology): “Refer to previous work [3], to collect the related facts from Freebase, we retain the triplets associated with those entities which are mapped with items in recommendation data.”