[1] Xie Chengyan, Dong Lu,. Graph-enhanced neural interactive collaborative filtering [J]. Journal of Southeast University (English Edition), 2022, 38 (2): 110-117. [doi:10.3969/j.issn.1003-7985.2022.02.002]

Copy

Graph-enhanced neural interactive collaborative filtering()

图神经网络增强交互协同过滤推荐算法

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

38

Issue:

2022 2

Page:

110-117

Research Field:

Automation

Publishing date:

2022-06-20

Info

Title:

Graph-enhanced neural interactive collaborative filtering

图神经网络增强交互协同过滤推荐算法

Author(s):

Xie Chengyan¹;  Dong Lu²

¹School of Automation, Southeast University, Nanjing 210096, China
²School of Cyber Science and Engineering, Southeast University, Nanjing 211189, China

谢程燕¹;  董璐²

¹东南大学自动化学院, 南京 210096; ² 东南大学网络空间安全学院, 南京211189

Keywords:

interactive recommendation systems;  cold-start;  graph neural network;  deep reinforcement learning

交互推荐系统;  冷启动;  图神经网络;  深度强化学习

PACS:

TP18

DOI:

10.3969/j.issn.1003-7985.2022.02.002

Abstract:

To improve the training efficiency and recommendation accuracy in cold-start interactive recommendation systems, a new graph structure called item similarity graph is proposed on the basis of real data from a public dataset. The proposed graph is built from collaborative interactions and a deep reinforcement learning-based graph-enhanced neural interactive collaborative filtering(GE-ICF)model. The GE-ICF framework is developed with a deep reinforcement learning framework and comprises an embedding propagation layer designed with graph neural networks. Extensive experiments are conducted to investigate the efficiency of the proposed graph structure and the superiority of the proposed GE-ICF framework. Results show that in cold-start interactive recommendation systems, the proposed item similarity graph performs well in data relationship modeling, with the training efficiency showing significant improvement. The proposed GE-ICF framework also demonstrates superiority in decision modeling, thereby increasing the recommendation accuracy remarkably.

为提升冷启动场景下交互推荐系统的训练效率和推荐精度, 基于一个公开数据集的真实数据, 根据用户交互构建了一种商品相似度连接图, 并设计了基于深度强化学习的图神经网络增强交互协同过滤模型(GE-ICF)来进行仿真实验.该模型基于深度强化学习框架, 采用图神经网络进行向量传播层设计, 在商品相似度连接图中挖掘商品间关系, 优化商品向量准确度.结果表明:在冷启动交互推荐场景下, 商品相似度连接图能够对大规模稀疏交互推荐数据关系进行高效建模, 有效提升训练效率;GE-ICF模型能够深入挖掘数据间关系, 进行更精确地决策建模, 有效提高了训练精度.

References:

[1] Wu Y, DuBois C, Zheng A X, et al. Collaborative denoising auto-encoders for top-n recommender systems [C]// Proceedings of the Ninth ACM International Conference on Web Search and Data Mining. Los Angeles, CA, USA, 2016: 153-162. DOI: 10.1145/2835776.2835837.
[2] Chen X, Xu H, Zhang Y, et al. Sequential recommendation with user memory networks [C]//Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining. Los Angeles, CA, USA, 2018: 108-116. DOI:10.1145/3159652.3159668.
[3] Zhao X, Xia L, Tang J, et al. Deep reinforcement learning for search, recommendation, and online advertising:A survey [J]. ACM SIGWEB newsletter, 2019: 1-15. DOI: 10.1145/3320496.3320500.
[4] Wang H, Wu Q, Wang H. Factorization bandits for interactive recommendation [C]// Thirty-first AAAI Conference on Artificial Intelligence. San Francisco, CA, USA, 2017: 2695-2702. DOI: 10.5555/3298483.3298627.
[5] Zhao X, Zhang W, Wang J. Interactive collaborative filtering [C]// Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. Los Angeles, CA, USA, 2013: 1411-1420. DOI: 10.1145/2505515.2505690.
[6] Wu Q, Wang H, Hong L, et al. Returning is believing: Optimizing long-term user engagement in recommender systems [C]// Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. Singapore, 2017: 1927-1936. DOI: 10.1145/3132847.3133025.
[7] Zou L, Xia L, Du P, et al. Pseudo Dyna-Q: A reinforcement learning framework for interactive recommendation [C]// Proceedings of the 13th International Conference on Web Search and Data Mining. Houston, TA, USA, 2020: 816-824. DOI: 10.1145/3336191.3371801.
[8] Chen H, Dai X, Cai H, et al. Large-scale interactive recommendation with tree-structured policy gradient [C]// Proceedings of the AAAI Conference on Artificial Intelligence. Honolulu, Hawaii, USA, 2019, 33(1): 3312-3320. DOI: 10.1609/aaai.v33i01.33013312.
[9] Zheng G, Zhang F, Zheng Z, et al. DRN: A deep reinforcement learning framework for news recommendation [C]// Proceedings of the 2018 World Wide Web Conference. Lyon, France, 2018: 167-176. DOI: 10.1145/3178876.3185994.
[10] Zou L, Xia L, Gu Y, et al. Neural interactive collaborative filtering [C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Xi’an, China, 2020: 749-758. DOI:10.1145/3397271.3401181.
[11] Wang X, He X, Wang M, et al. Neural graph collaborative filtering [C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. Paris, France, 2019: 165-174. DOI: 10.1145/3331184.3331267.
[12] Ma C, Ma L, Zhang Y, et al. Memory augmented graph neural networks for sequential recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence, New York, USA, 2020, 34(4): 5045-5052. DOI: 10.1609/aaai.v34i04.5945.
[13] Wang H, Zhao M, Xie X, et al. Knowledge graph convolutional networks for recommender systems [C]// The World Wide Web Conference. Los Angeles, CA, USA, 2019: 3307-3313. DOI: 10.1145/3308558.3313417.
[14] Lei Y, Pei H, Yan H, et al. Reinforcement learning based recommendation with graph convolutional q-network [C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Xi’an, China, 2020: 1757-1760. DOI: 10.1145/3397271.3401237.
[15] Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning [J]. Nature, 2015, 518(7540): 529-533. DOI:10.1038/nature14236.

Memo

Memo:

Biographies: Xie Chengyan(1996—), female, graduate; Dong Lu(corresponding author), female, doctor, associate professor, ldong90@seu.edu.cn.
Foundation items: The National Natural Science Foundation of China(No. 62173251), the Guangdong Provincial Key Laboratory of Intelligent Decision and Cooperative Control, the Fundamental Research Funds for the Central Universities.
Citation: Xie Chengyan, Dong Lu.Graph-enhanced neural interactive collaborative filtering[J].Journal of Southeast University(English Edition), 2022, 38(2):110-117.DOI:10.3969/j.issn.1003-7985.2022.02.002.

Common functions