Recommendation model based on generative adversarial network and social reconstruction

Junhua Gu; Xu Deng; Ningjing Zhang; Suqi Zhang; Junhua Gu; Xu Deng; Ningjing Zhang; Suqi Zhang

doi:10.3934/mbe.2023424

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 6: 9670-9692. doi: 10.3934/mbe.2023424

Previous Article Next Article

Research article

Recommendation model based on generative adversarial network and social reconstruction

1.
School of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin 300401, China
2.
Hebei Province Key Laboratory of Big Data Computing (Hebei University of Technology), Tianjin 300401, China
3.
School of Science, Tianjin University of Commerce, Tianjin 300134, China
4.
School of Information Engineering, Tianjin University of Commerce, Tianjin 300134, China

Academic Editor: Vladimir Mityushev

Received: 05 December 2022 Revised: 05 March 2023 Accepted: 05 March 2023 Published: 22 March 2023

Social relations can effectively alleviate the data sparsity problem in recommendation, but how to make effective use of social relations is a difficulty. However, the existing social recommendation models have two deficiencies. First, these models assume that social relations are applicable to various interaction scenarios, which does not match the reality. Second, it is believed that close friends in social space also have similar interests in interactive space and then indiscriminately adopt friends' opinions. To solve the above problems, this paper proposes a recommendation model based on generative adversarial network and social reconstruction (SRGAN). We propose a new adversarial framework to learn interactive data distribution. On the one hand, the generator selects friends who are similar to the user's personal preferences and considers the influence of friends on users from multiple angles to get their opinions. On the other hand, friends' opinions and users' personal preferences are distinguished by the discriminator. Then, the social reconstruction module is introduced to reconstruct the social network and constantly optimize the social relations of users, so that the social neighborhood can assist the recommendation effectively. Finally, the validity of our model is verified by experimental comparison with multiple social recommendation models on four datasets.
- recommendation algorithm,
- social recommendation,
- generative adversarial network,
- dynamic reconfiguration,
- graph neural network
Citation: Junhua Gu, Xu Deng, Ningjing Zhang, Suqi Zhang. Recommendation model based on generative adversarial network and social reconstruction[J]. Mathematical Biosciences and Engineering, 2023, 20(6): 9670-9692. doi: 10.3934/mbe.2023424

Related Papers:

Abstract

Social relations can effectively alleviate the data sparsity problem in recommendation, but how to make effective use of social relations is a difficulty. However, the existing social recommendation models have two deficiencies. First, these models assume that social relations are applicable to various interaction scenarios, which does not match the reality. Second, it is believed that close friends in social space also have similar interests in interactive space and then indiscriminately adopt friends' opinions. To solve the above problems, this paper proposes a recommendation model based on generative adversarial network and social reconstruction (SRGAN). We propose a new adversarial framework to learn interactive data distribution. On the one hand, the generator selects friends who are similar to the user's personal preferences and considers the influence of friends on users from multiple angles to get their opinions. On the other hand, friends' opinions and users' personal preferences are distinguished by the discriminator. Then, the social reconstruction module is introduced to reconstruct the social network and constantly optimize the social relations of users, so that the social neighborhood can assist the recommendation effectively. Finally, the validity of our model is verified by experimental comparison with multiple social recommendation models on four datasets.

References

[1]	Z. Batmaz, A. Yurekli, A. Bilge, A review on deep learning for recommender systems: challenges and remedies, Artif. Intell. Rev., 52 (2019), 1–37. https://doi.org/10.1007/s10462-018-9654-y doi: 10.1007/s10462-018-9654-y
[2]	K. Mariusz, W. Alicja, S. Krzysztof, S. Wlodzimierz, Beyond the Big Five personality traits for music recommendation systems, EURASIP J. Audio Speech Music Process., 2023 (2023), 1–17. https://doi.org/10.1186/s13636-022-00269-0 doi: 10.1186/s13636-022-00269-0
[3]	Y. Liu, J. Miyazaki, Knowledge-aware attentional neural network for review-based movie recommendation with explanations, Neural Comput. Appl., 35 (2022), 1–19. https://doi.org/10.1162/neco_a_01548 doi: 10.1162/neco_a_01548
[4]	C. Ju, J. Wang, G. Zhou, The commodity recommendation method for online shopping based on data mining, Multimedia Tools Appl., 78 (2019), 30097–30110. https://doi.org/10.1007/s11042-018-6980-7 doi: 10.1007/s11042-018-6980-7
[5]	B. Xu, H. Lin, L. Yang, Y. Lin, K. Xu, Cognitive knowledge-aware social recommendation via group-enhanced ranking model, Cognit. Comput., 14 (2022), 1055–1067. https://doi.org/10.1007/s12559-022-10001-x doi: 10.1007/s12559-022-10001-x
[6]	J. Liao, W. Zhou, F. Luo, J. Wen, X. Li, J. Zeng, SocialLGN: Light graph convolution network for social recommendation, Inf. Sci., 589 (2022), 595–607. https://doi.org/10.1016/j.ins.2022.01.001 doi: 10.1016/j.ins.2022.01.001
[7]	L. Wang, Y. Xiong, Y. Li, Y. Liu, A collaborative recommendation model based on enhanced graph convolutional neural network, J. Comput. Res. Dev., 58 (2021), 1987–1996.
[8]	Y. Zeng, Q. Mou, L. Zhou, A recommendation model of session perception based on Graph presentation learning, J. Comput. Res. Dev., 57 (2020), 590–603.
[9]	R. Ge, S. Chen, Graph convolutional network for recommender systems, J. Software, 31 (2020), 1101–1112. https://doi.org/10.13328/j.cnki.jos.005928 doi: 10.13328/j.cnki.jos.005928
[10]	I. Goodfellow, J. Pouget-Abadie, M. Mehdi, B. Xu, D. Warde-Farley, S. Ozair, et al., Generative adversarial networks, Commun. ACM, 63(2014), 139–144. https://doi.org/10.1145/3422622 doi: 10.1145/3422622
[11]	S. Wang, H. Jin, J. Sun, GAN image adversarial sample generation method, Comput. Sci. Explor., 15 (2021), 702–711.
[12]	G. Chen, Y. Liu, S. Zhong, X. Zhang, Musicality-novelty generative adversarial nets for algorithmic composition, in Proceedings of the 26th ACM international conference on Multimedia, 2018 (2018), 1607–1615. https://doi.org/10.1145/3240508.3240604
[13]	T. Bu, Z. Yang, S. Jiang, G. Zhang, H. Zhang, L. Wei, 3D conditional generative adversarial network-based synthetic medical image augmentation for lung nodule detection, Imaging Syst. Technol., 31 (2021), 670–681. https://doi.org/10.1002/ima.22511 doi: 10.1002/ima.22511
[14]	J. Li, J. Li, C. Wang, X. Zhao, Wide & deep generative adversarial networks for recommendation system, Intell. Data Anal., 27 (2023), 121–136. https://doi.org/10.3233/IDA-216400 doi: 10.3233/IDA-216400
[15]	C. Zhang, Y. Wang, L. Zhu, J. Song, H. Yin, Multi-graph heterogeneous interaction fusion for social recommendation, ACM Trans. Inf. Syst., 40 (2021), 1–26. https://doi.org/10.1145/3466641 doi: 10.1145/3466641
[16]	M. Jamali, M. Ester, A matrix factorization technique with trust propagation for recommendation in social networks, in Proceedings of the Fourth ACM Conference on Recommender Systems, 2010. https://doi.org/10.1145/1864708.1864736
[17]	W. Fan, Y. Ma, Q. Li, Y. He, Y. Zhao, J. Tang, et al., Graph neural networks for social recommendation, in The World Wide Web Conference, 2019 (2019), 417–426. https://doi.org/10.1145/3308558.3313488
[18]	L. Wu, P. Sun, Y. Fu, R. Hong, X. Wang, M. Wang, A neural influence diffusion model for social recommendation, in Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019 (2019), 235–244.
[19]	W. Hamilton, R. Ying, J. Leskovec, Inductive representation learning on large graphs, Adv. Neural Inf. Process. Syst., 2017 (2017), 30.
[20]	L. Wu, J. Li, P. Sun, R. Hong, Y. Ge, M. Wang, DiffNet++: A neural influence and interest diffusion network for social recommendation, IEEE Trans. Knowl. Data Eng., 34 (2020), 4753–4766. https://doi.org/10.1109/TKDE.2020.3048414 doi: 10.1109/TKDE.2020.3048414
[21]	L. Li, Z. Gan, Y. Cheng, J. Liu, Relation-aware graph attention network for visual question answering, in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019 (2019), 10313–10322.
[22]	Z. Yang, J. Qin, C. Lin, Y. Chen, R. Huang, Y. Qin, GANRec: A negative sampling model with generative adversarial network for recommendation, Expert Syst. Appl., 214 (2023), 119–155. https://doi.org/10.1016/j.eswa.2022.119155 doi: 10.1016/j.eswa.2022.119155
[23]	J. Wang, L. Yu, W. Zhang, Y. Gong, Y. Xu, B. Wang, et al., Irgan: A minimax game for unifying generative and discriminative information retrieval models, in Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval, 2017 (2017), 515–524. https://doi.org/10.1145/3077136.3080786
[24]	D. Chae, J. Kang, S. Kim, J. Lee, Cfgan: A generic collaborative filtering framework based on generative adversarial networks, in Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2018 (2018), 137–146. https://doi.org/10.1145/3269206.3271743
[25]	T. Sasagawa, S. Kawai, H. Nobuhara, Recommendation system based on generative adversarial network with graph convolutional layers, J. Adv. Comput. Intell. Intell. Inf., 25 (2021), 389–396. https://doi.org/10.20965/jaciii.2021.p0389 doi: 10.20965/jaciii.2021.p0389
[26]	J. Yu, M. Gao, H. Yin, J. Li, C. Gao, Q. Wang, Generating reliable friends via adversarial training to improve social recommendation, in 2019 IEEE International Conference on Data Mining (ICDM), 2019 (2019), 768–777. https://doi.org/10.1109/ICDM.2019.00087
[27]	J. Yu, H. Yin, J. Li, M. Gao, Z. Huang, L. Cui, Enhance social recommendation with adversarial graph convolutional networks, IEEE Trans. Knowl. Data Eng., 34 (2020), 3727–3739. https://doi.org/10.1109/TKDE.2020.3033673 doi: 10.1109/TKDE.2020.3033673
[28]	T. Zhao, J. McAuley, I. King, Leveraging social connections to improve personalized ranking for collaborative filtering, in Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management, 2014 (2014), 261–270. https://doi.org/10.1145/2661829.2661998
[29]	H. Liu, J. Wen, L. Jing, J. Yu, Leveraging implicit social structures for recommendation via bayesian generative model, Sci. China Inf. Sci., 65 (2022), 1–3. https://doi.org/10.1007/s11432-019-2884-0 doi: 10.1007/s11432-019-2884-0
[30]	Y. Yu, W. Qian, L. Zhang, R. Gao, A graph-neural-network-based social network recommendation algorithm using high-order neighbor information, Sensors, 22 (2022), 7122. https://doi.org/10.3390/s22197122 doi: 10.3390/s22197122
[31]	J. Lin, S. Chen, J. Wang, Graph neural networks with dynamic and static representations for social recommendation, in Database Systems for Advanced Applications: 27th International Conference, 13246 (2022), 264–271. https://doi.org/10.1007/978-3-031-00126-0_18

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)