Exploring High-Order User Preference on the Knowledge Graph for Recommender Systems

Wang, Hongwei; Zhang, Fuzheng; Wang, Jialin; Zhao, Miao; Li, Wenjie; Xie, Xing; Guo, Minyi

doi:10.1145/3312738

Cited by 160 publications

(163 citation statements)

References 37 publications

Supporting

Mentioning

159

Contrasting

Unclassified

Order By: Relevance

“…Many studies have been proposed [19] for the construction, inference and applications of KBs. Specially, several pioneering studies try to leverage existing KB information for improving the recommendation performance [17,18,21]. They apply a heuristic method for linking RS items with KB entities.…”

Section: Existing Datasets and Methodsmentioning

confidence: 99%

KB4Rec: A Data Set for Linking Knowledge Bases with Recommender Systems

Zhao

Yang

et al. 2019

Data Intellegence

View full text Add to dashboard Cite

To develop a knowledge-aware recommender system, a key data problem is how we can obtain rich and structured knowledge information for recommender system (RS) items. Existing datasets or methods either use side information from original recommender systems (containing very few kinds of useful information) or utilize private knowledge base (KB). In this paper, we present the first public linked KB dataset for recommender systems, named KB4Rec v1.0, which has linked three widely used RS datasets with the popular KB Freebase. Based on our linked dataset, we first preform some interesting qualitative analysis experiments, in which we discuss the effect of two important factors (i.e., popularity and recency) on whether a RS item can be linked to a KB entity. Finally, we present the comparison of several knowledge-aware recommendation algorithms on our linked dataset. KEYWORDSKnowledge-aware recommendation, recommender systems, knowledge base ACM Reference Format:

show abstract

Section: Existing Datasets and Methodsmentioning

confidence: 99%

KB4Rec: A Data Set for Linking Knowledge Bases with Recommender Systems

Zhao

Yang

et al. 2019

Data Intellegence

View full text Add to dashboard Cite

show abstract

“…The two main methods of introducing a knowledge graph into the recommendation system are path-based methods [12], [15]- [17] and embedding-based methods [13], [14], [18], [19]. And it has been applied in many scenarios such as news recommendation [13], music recommendation [20], paper recommendation [21], question answering [22], text classification [23], community detection [24] and machine reading [25].…”

Section: B Knowledge Graphmentioning

confidence: 99%

“…• RippleNet [12]: RippleNet is a memory-network-like approach that propagates users' preferences on the knowledge graph.…”

Section: Baselinesmentioning

confidence: 99%

Knowledge Graph Enhanced Third-Party Library Recommendation for Mobile Application Development

Chen

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

With the prevalence of smart terminal devices and the rapid development of the mobile Internet, mobile application markets become increasingly prosperous. Third-party libraries have played an essential role in mobile application development. These libraries can shorten development time, increase development efficiency, and improve development quality. Currently, a large number of third-party libraries have been published, which puts a heavy burden on developers in selecting appropriate libraries. Towards this issue, in this paper, we propose a novel third-party library recommendation approach by integrating topic modeling and knowledge graph techniques. In the topic modeling component, we extract topics from textual application descriptions and make recommendations based on libraries used by applications that share similar topics with the new application to develop. In the knowledge graph component, we leverage knowledge graph to incorporate structured information of third-party libraries and applications, as well as the interaction information of applications and libraries for the recommendation. Experiments conducted on a real-world dataset show that our proposed approach outperforms several state-of-the-art approaches in terms of recommendation performance. INDEX TERMS Third-party library recommendation, mobile app, knowledge graph, topic modeling, MKR. LI YAO received the B.E. degree from Wuhan University, Wuhan, China, in 2019, where he is currently pursuing the master's degree with the School of Computer Science. His current research interests include services computing, recommender systems, and natural language processing.

show abstract

“…If the equals to 0, it denote th user did not rate the th item. We assume that ( ), ( ), and the calculation of user factor and item factor are shown as the formula (2) , (3).…”

Section: Probabilistic Matrix Factorization and Problem Settingmentioning

confidence: 99%

“…Of course. With the development of MF, many improved algorithms based on MF have been proposed, such as using knowledge graph embedding [3] and integrating the social network [4].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Online Collaborative Filtering by Integrating Social Network

2019

Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering

View full text Add to dashboard Cite

In recent years, researchers have done a lot of work to enhance online collaborative filtering (OCF) performance. Compared to most of the offline collaborative filtering (offline CF), the online collaborative filtering algorithm has three advantages: the low cost of retraining the model, dynamically tracing the user behavior habits and capturing the change of the item popularity. Many OCF algorithms extract user interests and item popularity features by updating algorithms model in time. But most of OCF ignore the similarity of users or items by updating all users' features or all items' features. In this study, we aim to integrate social network to improve the OCF performance. In order to achieve the goal, we propose two new methods by introducing user similarity which obtains from user social network to online collaborative filtering based on the Probabilistic Matrix Factorization (PMF) frame. One of the methods, which we called OCFUSim_I, is to calculate the similarity of users and find the neighbors of user, then adding the neighbors to the OCF. Another method, called OCFUSim_II, is to add similarity among users to OCF model. We conduct the experiments on three public datasets: MovieLens100K, MovieLens1M and HetRec2011 datasets. The experimental results show that our algorithms achieve better performance than several baseline approaches.

show abstract

Exploring High-Order User Preference on the Knowledge Graph for Recommender Systems

Cited by 160 publications

References 37 publications

KB4Rec: A Data Set for Linking Knowledge Bases with Recommender Systems

KB4Rec: A Data Set for Linking Knowledge Bases with Recommender Systems

Knowledge Graph Enhanced Third-Party Library Recommendation for Mobile Application Development

Enhancing Online Collaborative Filtering by Integrating Social Network

Contact Info

Product

Resources

About