Recognize News Transition from Collective Behavior for News Recommendation

被引：5

作者：

Meng, Qing ^{[1
,2
]}

Yan, Hui ^{[1
]}

Liu, Bo ^{[1
,3
]}

Sun, Xiangguo ^{[4
]}

Hu, Mingrui ^{[1
]}

Cao, Jiuxin ^{[3
,5
]}

机构：

[1] Southeast Univ, Sch Comp Sci & Engn, Southeast Univ Rd 2, Nanjing 211189, Peoples R China

[2] Hohai Univ, Coll Comp & Informat, Focheng West Rd 8, Nanjing 211100, Peoples R China

[3] Purple Mt Labs, Mo Zhou Dong Lu 11, Nanjing 211189, Peoples R China

[4] Chinese Univ Hong Kong, Dept Syst Engn & Engn Management, Cent Ave, Hong Kong, Peoples R China

[5] Southeast Univ, Sch Cyber Sci & Engn, Rd 2, Nanjing 211189, Peoples R China

来源：

ACM TRANSACTIONS ON INFORMATION SYSTEMS | 2023年 / 41卷 / 04期

基金：

中国国家自然科学基金;

关键词：

News recommendation; transition graph; graph attention network; collective behavior;

D O I：

10.1145/3578362

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In the news recommendation, users are overwhelmed by thousands of news daily, which makes the users' behavior data have high sparsity. Therefore, only considering a single user's personalized preferences cannot support the news recommendation. How to improve the relatedness of news and users and reduce data sparsity has become a hot issue. Recent studies have attempted to use graph models to enrich the relationship between users and news, but they are still limited to modeling the historical behaviors of a single user. To fill the gap, we integrate user-news relationships and the overall user historical clicked news sequences to construct a global heterogeneous transition graph. And a refinement approach is proposed to recognize the news transition patterns in the graph. Based on the global heterogeneous transition graph, we propose a heterogeneous transition graph attention network to capture the common behavior patterns of most users to enhance the representation of user interest. Fusing the users' personalized and common interest, we propose the GAINREC model to recommend news effectively. Extensive experiments are conducted on two public news recommendation datasets, and the results show the superiority of the proposed GAINREC model compared with the state-of-the-art news recommendation models. The implementation of our model is available at https://github.com/newsrec/GAINRec.

引用

页数：30

共 61 条

[1]

Bansal Trapit., 2015, Proceedings of the 9th ACM Conference on Recommender Systems, P195

[2]

Billsus D., 1999, Proceedings of the Third International Conference on Autonomous Agents, P268, DOI 10.1145/301136.301208

[3]

Bordes A., 2013, P 26 INT C NEURAL IN, P2787

[4]

Bruna J, 2014, Arxiv, DOI arXiv:1312.6203

[5]

Capelle M., 2012, P 2 INT C WEB INT MI, DOI 10.1145/2254129.2254163

[6] Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning [J].

Chen, Tong ;

Yin, Hongzhi ;

Ren, Jie ;

Huang, Zi ;

Zhang, Xiangliang ;

Wang, Hao .

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (02) :2103-2117

[7]

Das AbhinandanS., 2007, P 16 INT C WORLD WID

[8]

Defferrard M, 2016, ADV NEUR IN, V29

[9]

Del Re Emanuela C., 2013, Collective Behavior, P422, DOI DOI 10.1007/978-1-4020-8265-8_1711

[10]

Devlin J, 2019, Arxiv, DOI [arXiv:1810.04805, DOI 10.48550/ARXIV.1810.04805]

← 1 2 3 4 5 6 7 →