Research on Group Preference Fusion Strategy Based on Two-Layer Attention Mechanism

doi:10.3778/j.issn.1002-8331.2205-0437

Abstract

Abstract: One of the current research hotspots of recommender systems and its evolution trend is that personalized recommendation gradually shifts from focusing on individual recommendation to focusing on group recommendation. At present, most group recommendation methods are accustomed to adopting a predefined static strategy when choosing a preference fusion strategy, and the characteristics of the static strategy make the algorithm unable to maximize the simulation of the real process of group decision-making. On the basis of previous research, this paper proposes a group recommendation method based on a two-layer attention mechanism, which fully takes into account the differences and mutual influence of group users, as well as the decision-making power in different fields. The attention weight of each member in the group is calculated to other members, the group member feature vector is obtained, and then the attention weight of each member in selecting a certain item is calculated, and the preference vector for the item for the group is generated. The interaction between group users and the process of group decision-making are fully restored. By comparing the CAMRa2011 and Meetup datasets with COM, SIG, AGR, AGREE, FastGR and other methods under different parameter conditions, the two indicators of normalized discount cumulative gain and hit rate are higher than the baseline model, is up to 0.025 4 and 0.030 7.

Key words: group recommendation, attention mechanism, preference fusion strategy, recommendation algorithm

摘要： 当前推荐系统研究热点及其演变趋势之一是个性化推荐由关注个体推荐逐步转向关注群体推荐。目前多数群组推荐方法在选择偏好融合策略时习惯采用预定义的静态策略，而静态策略的特点就导致算法无法最大化模拟出群组决策的真实过程。在前人研究的基础之上提出一种基于双层注意力机制的群组推荐方法，该方法充分考虑到群体用户的差异性和相互影响，以及对于不同领域的决策权等问题。计算群组内每位成员对其他成员的注意力权重，获得群组成员特征向量，再计算每个成员在选择某一个项目的注意力权重，为群组生成对于该项目的偏好向量，以此来充分还原群组用户之间的交互以及群组决策的过程。通过在CAMRa2011和Meetup数据集上与COM、SIG、AGR、AGREE、FastGR等方法在不同参数条件下进行了对比，在归一化折扣累计增益和命中率两个指标上，相较基线模型平均提高了0.025 4和0.030 7。

关键词: 群组推荐, 注意力机制, 偏好融合策略, 推荐算法

MEI Yuzhu, HU Zhulin, ZHU Xinjuan. Research on Group Preference Fusion Strategy Based on Two-Layer Attention Mechanism[J]. Computer Engineering and Applications, 2023, 59(9): 272-279.

梅雨竹, 胡竹林, 朱欣娟. 融合双层注意力机制的群组偏好融合策略研究[J]. 计算机工程与应用, 2023, 59(9): 272-279.

References

[1] REN Y，TOMKO M，SALIM F D，et al.A location-query-browse graph for contextual recommendation[J].IEEE Transactions on Knowledge and Data Engineering，2017，30（2）：204-218.
[2] HE X，GAO M，KAN M Y，et al.Birank：towards ranking on bipartite graphs[J].IEEE Transactions on Knowledge and Data Engineering，2016，29（1）：57-71.
[3] CAO D，NIE L，HE X，et al.Version-sensitive mobile app recommendation[J].?Information Sciences，2017，381：161-175.
[4] 童小凯，朱欣娟，王西汉，等.数字文化资源知识图谱多目标跨域推荐方法[J/OL].计算机工程与应用：1-11[2022-05-08]. http：//kns.cnki.net/kcms/detail/11.2127.1tp.20220411.
553.011.html.
TONG X K，ZHU X J，WANG X H，et al.Knowledge graph multi-target cross-domain recommendation on digital cultural resources[J/OL].Computer Engineering and Applications：1-11[2022-05-08].http：//kns.cnki.net/kcms/detail/11. 2127.tp.20220411.1553.011.html.
[5] ZHANG C，ZHANG H，WANG J.Personalized restaurant recommendation method combining group correlations and customer preferences[J].Information Sciences，2018（454/455）：128-143.
[6] XU J C.Family shopping recommendation system using user profile and behavior data[J].arXiv：1708.07289，2017.
[7] 谢浩然，陈协玲，郑国城，等.人工智能赋能个性化学习：E-Learning推荐系统研究热点与展望[J].现代远程教育研究，2022，34（3）：15-23.
XIE H R，CHEN X L，ZHENG G C，et al.AI enabling personalized learning：research hotspot and prospect of E?Learning recommendation system[J].Modern Distance Education Research，2022，34（3）：15-23.
[8] 许晓明，梅红岩，于恒，等.基于偏好融合的群组推荐方法研究综述[J].小型微型计算机系统，2020，41（12）：2500-2508.
XU X M，MEI H Y，YU H，et al.Review of group recommendation method based on preference fusion[J].Journal of Chinese Computer Systems，2020，41（12）：2500-2508.
[9] 朱欣娟，童小凯，王西汉，等.一种融合协同因子的知识图谱传播推荐模型[J].西安工程大学学报，2022，36（2）：79-86.
ZHU X J，TONG X K，WANG X H，et al.A graph recommender model for knowledge graph propagation with collaborative factors[J].Journal of Xi’an Polytechnic University，2022，36（2）：79-86.
[10] 张玉洁，杜雨露，孟祥武.组推荐系统及其应用研究[J].计算机学报，2016，39（4）：745-764.
ZHANG Y J，DU Y L，MENG X W.Research on group recommendation system and their application[J].Chinese Journal of Computers，2016，39（4）：745-764.
[11] BALTRUNAS L，MAKCINSKAS T，RICCI F.Group recommendations with rank aggregation and collaborative filtering[C]//Proceedings of the Fourth ACM Conference on Recommender Systems，2010：119-126.
[12] AMER-YAHIA S，ROY S B，CHAWLAT A，et al.Group recommendation：semantics and efficiency[J].Proceedings of the VLDB Endowment，2009，2（1）：754-765.
[13] BORATTO L，CARTA S.State-of-the-art in group recommendation and new approaches for automatic identification of groups[C]//Information Retrieval and Mining in Distributed Environments.Berlin，Heidelberg：Springer，2010：1-20.
[14] QUINTARELLI E，RABOSIO E，TANCA L.Recommending new items to ephemeral groups using contextual user influence[C]//Proceedings of the 10th ACM Conference on Recommender Systems，2016：285-292.
[15] LIU X，TIAN Y，YE M，et al.Exploring personal impact for group recommendation[C]//Proceedings of the 21st ACM International Conference on Information and Knowledge Management，2012：674-683.
[16] YUAN Q，CONG G，LIN C Y.COM：a generative model for group recommendation[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，2014：163-172.
[17] VINH T D Q，PHAM T A N，CONG G，et al.Attention-based group recommendation[J].arXiv：1804.04327，2018.
[18] CAO D，HE X，MIAO L，et al.Attentive group recommendation[C]//The 41st International ACM SIGIR Conference on Research ＆ Development in Information Retrieval，2018：645-654．
[19] 尚文倩，曹原.FastGR：一种基于神经协同过滤的群组推荐算法[J].南京师范大学学报（工程技术版），2022，22（2）：29-34.
SHANG W Q，CAO Y.FastGR：a group recommendation algorithm based on neural collaborative filtering[J].Journal of Nanjing Normal University（Engineering Technology Edition），2022，22（2）：29-34.
[20] YIN H，WANG Q，ZHENG K，et al.Social influence-based group representation learning for group recommendation[C]//2019 IEEE 35th International Conference on Data Engineering（ICDE），2019：566-577.
[21] HE X，CHUA T S.Neural factorization machines for sparse predictive analytics[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval，2017：355-364.
[22] 王刚，蒋军，王含茄.社会化推荐研究综述[J].计算机科学，2018，45（S2）：37-42.
WANG G，JIANG J，WANG H R.Review of social recommendation[J].Computer Science，2018，45（S2）：37-42.
[23] 胡川，孟祥武，张玉洁，等.一种改进的偏好融合组推荐方法[J].软件学报，2018（10）：1-12.
HU C，MENG X W，ZHANG Y J，et al.Enhanced group recommendation method based on preference aggregation[J].Journal of Software，2018（10）：1-12.
[24] HUANG Z，XU X，ZHU H，et al.An efficient group recommendation model with multiattention-based neural networks[J].IEEE Transactions on Neural Networks and Learning Systems，2020，31（11）：4461-4474.
[25] CHEN J，ZHANG H，HE X，et al.Attentive collaborative filtering：multimedia recommendation with item-and component-level attention[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval，2017：335-344.
[26] XIAO J，YE H，HE X，et al.Attentional factorization machines：learning the weight of feature interactions via attention networks[J].arXiv：1708.04617，2017.
[27] 高广尚.深度学习推荐模型中的注意力机制研究综述[J].计算机工程与应用，2022，58（9）：9-18.
GAO G S.Survey on attention mechanisms in deep learning recommendation models[J].Computer Engineering and Applications，2022，58（9）：9-18.
[28] JHAMB Y，EBESU T，FANG Y.Attentive contextual denoising autoencoder for recommendation[C]//Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval，2018：27-34.
[29] TAY Y，LUU A T，HUI S C.Multi-pointer co-attention networks for recommendation[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining，2018：2309-2318.