基于深度学习的群组推荐方法研究综述

郑楠; 章颂; 刘玉桥; 王雨桐; 王飞跃

doi:10.16383/j.aas.c230781

基于深度学习的群组推荐方法研究综述

doi: 10.16383/j.aas.c230781 cstr: 32138.14.j.aas.c230781

郑楠^{1, 2,},
章颂^{1, 2,},
刘玉桥^{1, 2,},
王雨桐^3,,
王飞跃^{2, 3,}

1.
中国科学院自动化研究所多模态人工智能系统全国重点实验室北京 100190
2.
中国科学院大学人工智能学院北京 100049
3.
中国科学院自动化研究所复杂系统管理与控制国家重点实验室北京 100190

基金项目: 国家重点研究发展计划 (2023YFC3304104), 国家自然科学基金 (U1811463) 资助

详细信息

作者简介:
郑楠：中国科学院自动化研究所多模态人工智能系统全国重点实验室副研究员. 主要研究方向为复杂系统, 综合集成, 数据挖掘, 个性化推荐. E-mail: nan.zheng@ia.ac.cn

章颂：中国科学院自动化研究所多模态人工智能系统全国重点实验室博士研究生. 主要研究方向为复杂系统, 综合集成, 语言推理, 推荐系统.Email: zhangsong2022@ia.ac.cn

刘玉桥：中国科学院自动化研究所多模态人工智能系统全国重点实验室硕士研究生. 主要研究方向为数据挖掘, 推荐系统, 自然语言处理. Email: liuyuqiao2022@ia.ac.cn

王雨桐：中国科学院自动化研究所助理研究员. 2021 年获得中国科学院大学控制理论与控制工程专业博士学位. 主要研究方向为计算机视觉.E-mail: yutong.wang@ia.ac.cn

王飞跃：中国科学院自动化研究所复杂系统管理与控制国家重点实验室研究员. 主要研究方向为智能系统和复杂系统的建模、分析与控制. 本文通信作者.E-mail: feiyue.wang@ia.ac.cn

计量
- 文章访问数: 90
- HTML全文浏览量: 43
- 被引次数: 0
出版历程
- 收稿日期: 2023-12-18
- 录用日期: 2023-05-12
- 网络出版日期: 2024-09-27

A Comprehensive Review of Group Recommendation Methods Based on Deep Learning

ZHENG Nan^{1, 2
,},
ZHANG Song^{1, 2
,},
LIU Yu-Qiao^{1, 2
,},
WANG Yu-Tong^3
,,
WANG Fei-Yue^{2, 3
,}

1.
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 1000190
2.
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049
3.
State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190

Funds: Supported by National Key Research and Development Program of China (2023YFC3304104) and National Natural Science Foundation of China (U1811463)

More Information

Author Bio:
ZHENG Nan　Associate professor at the State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences. Her research interest covers complex systems, metasynthesis, data mining and personalized recommendations

ZHANG Song　Ph. D. candidate at the State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences. His research interests include complex systems, metasynthesis, natural language reasoning and recommender system

LIU Yu-Qiao　Master candidate at the State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences. His research interest covers data mining, recommendation system and natural language processing

WANG Yu-Tong　Assistant professor at the Institute of Automation, Chinese Academy of Sciences. She received her Ph.D. degree in control theory and control engineering from the University of Chinese Academy of Sciences in 2021. Her main research interest is computer vision

WANG Fei-Yue　Professor at the State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences. His research interest covers modeling, analysis, and control of intelligent systems and complex systems. Corresponding author of this paper

摘要

摘要: 群组推荐在信息检索与数据挖掘领域近年来备受关注, 其旨在从海量候选集中挑选出一组用户可能感兴趣的项目. 随着深度学习技术的不断发展, 基于深度学习的群组推荐方法大量涌现. 本文首先介绍了群组推荐问题的背景知识, 然后系统综述了数据获取方法, 全面评述了近年来基于深度学习的群组推荐算法, 并进行了系统分类与深入分析. 此外, 还归纳了适用于深度学习方法的群组推荐数据集和评价方法, 对各类推荐算法进行了对比实验分析与讨论. 最后, 针对本领域的研究难点进行了深入探讨, 并提出了未来有待深入研究的方向.
- 群组推荐 /
- 推荐系统综述 /
- 深度学习 /
- 群组表示学习
Abstract: Group recommendation has emerged as a highly active research topic in the fields of information retrieval and data mining in recent years. Its objective is to select a group of items from a large candidate set that is likely to be of interest to a set of users. With the advancement of deep learning in recent years, numerous group recommendation methods based on deep learning have been proposed. This paper provides a brief introduction to the background knowledge of this problem. It reviews the methods of data acquisition in group recommendation and conducts a comprehensive review, systematic classification, and in-depth analysis of group recommendation algorithms based on deep learning in recent years. In addition, this paper also outlines some group recommendation datasets and evaluation methods suitable for deep learning methods, and conducts comparative experimental analysis and discussion on various recommendation algorithms. Finally, the research challenges in this field were analyzed, and valuable future research directions were discussed.
- Group recommendation /
- recommender system overview /
- deep learning /
- group representation learning
注释:

1) 1¹ 豆瓣小组 (https://www.douban.com/group/explore) 是信息获取和分享平台豆瓣网的重要组成部分, 用户可以根据个人兴趣、剧名、电影、宠物、化妆品、摄影、旅行等主题创建或加入各种小组, 与其他成员讨论和分享相关话题. 每个小组都有自己的规则和特色, 成员可以发布帖子、参与讨论、分享观点和经验等.² Meetup是美国在线社交平台, 通过收集并分析人们的兴趣爱好和住址等信息, 帮助具有共同兴趣的人组成群组并安排线下聚会.³ Weeplaces是一种基于位置的可视化地图服务, 记录了用户在基于地理位置的社交网络中的签到历史. Yelp是美国最大的点评网站, 用户可以在网站中对商户进行评分、提交评论, 以及分享购物体验等.

2) 2⁴ Flickr是一个提供图片存储和分享服务的网站, 用户可以上传、存储和分享自己的照片和视频, 用户还可以在这里浏览他人的作品、参与讨论和互相交流.

3) 3⁵ 元路径是一种定义在异构图上的路径模式, 形式化表示为$ {\mathrm{A}}_{1}\stackrel{{\mathrm{R}}_{1}}{\to }{\mathrm{A}}_{2}\stackrel{{\mathrm{R}}_{2}}{\to }\cdots \stackrel{{\mathrm{R}}_{\mathrm{l}}}{\to }{\mathrm{A}}_{l+1} $ (简写为$ {\mathrm{A}}_{1}{\mathrm{A}}_{2}\cdots {\mathrm{A}}_{l+1} $), 可以理解为在$ {\mathrm{A}}_{1} $和$ {\mathrm{A}}_{l+1} $之间是一种混合的链接关系, 该关系可以形式化地表示为$ \mathrm{R}={\mathrm{R}}_{1}\diamond {\mathrm{R}}_{2}\cdots \diamond {\mathrm{R}}_{\mathrm{l}} $.

HTML全文

图 1 群组推荐示意图

Fig. 1 Diagram of group recommendation

下载: 全尺寸图片幻灯片

图 2 群组交互关系图

Fig. 2 Diagram of group interaction

下载: 全尺寸图片幻灯片

图 3 基于深度学习的群组推荐系统框架

Fig. 3 Framework of a deep learning based group recommendation system

下载: 全尺寸图片幻灯片

图 4 偏好聚合策略与评分聚合策略的过程对比

Fig. 4 Comparison of the process of preference aggregation strategy and rating aggregation strategy

下载: 全尺寸图片幻灯片

图 5 DLGR算法示例图^[39]

Fig. 5 Example diagram of DLGR algorithm

下载: 全尺寸图片幻灯片

图 6 PIT算法示意图^[18]

Fig. 6 Schematic diagram of PIT algorithm

下载: 全尺寸图片幻灯片

图 7 AGREE模型结构图^[46]

Fig. 7 Diagram of AGREE model structure

下载: 全尺寸图片幻灯片

图 8 MoSAN算法结构图^[47]

Fig. 8 Diagram of MoSAN algorithm structure

下载: 全尺寸图片幻灯片

图 9 GRADI算法结构图^[48]

Fig. 9 Diagram of GRADI algorithm structure

下载: 全尺寸图片幻灯片

图 10 GLIF算法框图^[49]

Fig. 10 Block diagram of GLIF algorithm

下载: 全尺寸图片幻灯片

图 11 KGAG模型示意图^[53]

Fig. 11 Schematic diagram of KGAG model

下载: 全尺寸图片幻灯片

图 12 HetGRec算法结构图^[54]

Fig. 12 Diagram of HetGRec algorithm structure

下载: 全尺寸图片幻灯片

图 13 GroupIM算法结构示意图^[55]

Fig. 13 Schematic diagram of GroupIM algorithm structure

下载: 全尺寸图片幻灯片

图 14 GBERT算法预训练阶段流程框图^[60]

Fig. 14 GBERT algorithm pre-training phase flowchart

下载: 全尺寸图片幻灯片

图 15 群组偏好表示方法分类总结

Fig. 15 Classification summary of group preference representation methods

下载: 全尺寸图片幻灯片

图 16 神经协同过滤框架^[66]

Fig. 16 Framework of neural collaborative filtering

下载: 全尺寸图片幻灯片

表 1 数学符号说明

Table 1 Explanation of mathematical symbols

符号	说明
$ U=\left\{{u}_{1},\;{u}_{2},\;{\cdots ,\;u}_{n}\right\} $	用户集合
$ V=\left\{{v}_{1},\;{v}_{2},\;{\cdots ,\;v}_{m}\right\} $	项目集合
$ G=\left\{{g}_{1},\;{g}_{2},\;{\cdots ,\;g}_{s}\right\} $	群组集合
$ \mathit{A}={\left[{a}_{li}\right]}_{s\times m} $	〈群组-项目〉交互矩阵
$ \mathit{B}={\left[{b}_{ij}\right]}_{n\times m} $	〈用户-项目〉交互矩阵
$ \mathit{C}={\left[{c}_{lj}\right]}_{s\times n} $	〈群组-用户〉交互矩阵
$ {\mathcal{G}}_{UV} $	〈用户-项目〉交互图
$ {R}_{V}\left(u\right) $	与用户$ u\mathrm{有} $过交互的所有项目集合
$ \mathscr{p} $	元路径
$ {\mathcal{N}}^{\mathscr{p}}\left(u\right) $	节点$ u $基于元路径$ \mathscr{p} $找到的近邻集合
$ {u}_{t}^{g} $	群组$ g $中的第$ t $个成员, $ {u}_{t}^{g}\in U $
$ f:V\to \mathbf{R} $	由项目集到实数域的函数 (映射) $ f $
$ {\vec{e}}_{u},\;{\vec{e}}_{v},\;{\vec{e}}_{g} $	用户$ u $, 项目$ v $和群组$ g $的ID嵌入向量
$ {\vec{h}}_{u},\;{\vec{h}}_{v},\;{\vec{h}}_{g} $	$ {\vec{e}}_{u},\;{\vec{e}}_{v},\;{\vec{e}}_{g} $经过编码后的向量表示

下载: 导出CSV

表 2 群组偏好表示学习方法对比

Table 2 Comparison of learning methods for group preference representation

表示学习层技术	特点	不足
基于启发式聚合策略的群组偏好表示方法	结合个性化推荐方法和预定义的聚合策略完成群组推荐任务, 方法简单高效	无法根据交互数据自身的模式来学习成员之间, 成员与群组之间的影响力
基于概率模型的群组偏好表示方法	建模群组的生成过程, 采用潜变量表示用户对群组或其他成员的影响力	较依赖于先验分布的假设, 无法动态地建模成员用户的影响力
基于注意力机制的群组偏好表示方法	采用注意力机制主动从用户交互记录等信息中学习成员的影响力	数据稀疏性可能导致的模型训练低效, 使得学习到的影响力不准确
基于图神经网络的群组偏好表示方法	采用图神经网络建模用户、群组和项目之间的高阶交互关系, 并结合注意力算子计算信息沿着关系传播的权重, 有效地缓解因数据稀疏导致推荐效果不佳的问题	可能需要用户的社交信息来构建网络, 较难实现; 针对冷启动群组, 需要重新训练网络
增加约束类的群组偏好表示方法	采用增加约束的方式降低解空间的规模, 基于多任务之间的共性特征, 提升模型优化的效果	较依赖于预训练数据集的质量; 较依赖于任务之间的关联强度
引入外部信息的群组偏好表示方法	通过引入外部信息的方式, 增强群组偏好的表示学习, 如社交网络信息、项目描述信息和用户评论信息等	外部信息较难获取等问题

下载: 导出CSV

表 3 群组推荐数据集信息

Table 3 Group recommendation dataset information

数据集	类别	内容
CAMRa2011^{[46, 48−49, 54, 62, 67]}	电影	包含602个用户组成的290个群组对7710部电影的评分.
MovieLens 1M^{[47, 49, 53−54, 68−69]}	电影	包含上百万评分记录的电影数据集, 由于该数据集不存在显示的群组, 通常根据用户相似度构建群组.
Weeplaces^{[55, 60]}	签到	由于该数据集中不存在显式的群组, 通常将15分钟以内在同一地点签到且存在朋友关系的用户视为一个群组, 形成包含8 643个用户打卡25 081个商户的22 733个群组.
Yelp^{[53, 55, 60, 63, 70−71]}	点评	包含34 504个用户对22 611个餐厅的点评. 由于该数据不存在显示的群组, 将在同一时间段内打卡同一个餐厅且存在社交关系的用户视为一个群组, 形成24 103个群组.
Douban^{[55, 60, 63−64, 70−71]}	活动	包含70 743个用户对60 028个活动的评分. 由于该数据不存在显示的群组, 将参加同一活动的用户视为一个群组, 形成109 538个群组.
Meetup^{[47−48, 52, 64, 68, 72]}	活动	按照事件的地点, 该数据集分Meetup-NYC (纽约市) 和Meetup-Cal (加利福尼亚). 这两个数据集均没有显示的群组, 通常将参加同一个事件的人视为一个群组. 其中, Meetup-NYC包含46 619个用户、9428个群组、2 326个项目. 每个用户平均交互记录为4.23, 每个群组的平均交互记录为4.05; Meetup-Cal包含59 486个用户、15 207个群组、4 472个项目. 每个用户平均交互记录为4.55, 每个群组的平均交互记录为3.41.
BookCrossing^[69]	书籍	包含 278 858名用户, 提供271 379本书的1 149 780个评分. 该数据集不包含显示的群组, 通常通过寻找相似用户构建群组.
Jester Joke^[73]	笑话	包含73 421个用户对 100 个笑话作的 410 万次评分, 评分范围是-10 ~ 10 的连续实数. 不包含分组信息, 通过计算用户相似度来进行分组.
Netflix^[74]	电影	包含480 507个用户对17770部电影的100 480 507条评价数据, 其中评分以5分制为基准. 不包含分组信息, 利用用户的偏好相似信息构造群组.

下载: 导出CSV

表 4 不同表示层算法在三个常见的持续性群组数据集上的推荐效果 (%)

Table 4 The recommendation performance of different presentation layer algorithms on three common persistent group datasets (%)

数据集	CAMRa2011				MS				MR
Metric	H@5	H@10	N@5	N@10	H@5	H@10	N@5	N@10	H@5	H@10	N@5	N@10
NCF-AVG	58.33	77.65	39.69	46.25	59.19	83.15	47..35	52.21	63.52	78.42	45.32	50.29
NCF-LM	57.14	77.13	39.63	45.81	63.31	81.07	45.92	51.19	63.32	78.46	45.18	50.03
NCF-MS	57.19	75.12	38.50	44.41	64.43	82.25	46..62	51.98	62.35	77.85	44.43	49.02
AGREE	58.50	77.93	40.25	46.62	65.96	83.23	47.33	52..94	64.10	79.01	45.76	50.69
MoSAN	58.73	77.51	40.24	46.31	66.41	81.77	47.02	51.63	65.21	79..75	45.23	50.54
GAME	59.09	78.64	40.23	46.70	65.97	83.22	48.38	53.25	65.55	79.32	46.41	50.10
GLIF	59.18	78.93	40.30	46.73	66.43	83.55	48.20	53.44	65.61	79.93	46.43	51.07
KGAG	59.83	79.83	40.35	47.01	66.41	83.55	49.03	54.01	65.80	79.99	46.63	51.39
HetGRec	62.31	81.95	42.33	48.90	68.32	86.15	50.24	55.39	68.01	82.20	48.32	53.39

下载: 导出CSV

表 5 不同算法在三个常见的临时性群组数据集上的推荐效果 (%)

Table 5 The recommendation performance of different algorithms on three common temporary group datasets (%)

数据集	Weeplaces				Yelp				Douban
Metric	R@5	R@10	N@5	N@10	R@5	R@10	N@5	N@10	R@5	R@10	N@5	N@10
NCF-AVG	20.91	29.56	11.06	12.90	21.84	29.14	15.08	16.43	35.33	43.23	22.98	24.70
NCF-LM	20.32	28.33	10.49	12.19	23.22	31.44	16.04	17.20	44.29	49.56	31.91	33.10
NCF-MS	19.75	28.72	10.74	12.65	21.38	28.22	14.50	15.08	35.36	42.10	23.04	24.51
AGREE	20.53	29.09	11.40	13.22	24.16	30.98	16.80	17.63	45.95	51.22	33.39	34.57
MoSAN	31.81	37.71	26.25	28.15	46.57	50.61	34.66	36.18	47.10	52.22	36.12	37.24
GAME	41.97	48.53	28.90	30.35	46.44	51.94	35.32	36.52	58.76	77.52	40.29	46.33
KGAG	41.50	48.42	28.96	30.54	46.35	51.87	35.23	36.47	58.64	77.49	40.25	46.29
GroupIM	41.98	48.53	30.35	31.31	48.4	52.39	35.78	36.39	63.54	78.44	45.93	52.19
GBERT	49.43	52.82	35.31	36.43	48.67	53.14	37.46	38.11	65.20	79.90	47.22	54.58

下载: 导出CSV

参考文献(91)

[1]	Everbright Securities, Tang Jia-Rui, Tian Ran, Liang Dan-Hui. In-depth report on the E-commerce industry: Deepening online consumption mindset and actively exploring new consumption scenarios [Online], available: https://baijiahao.baidu.com/s?id=1760070652649669963&wfr=spider&for=pc, March 11, 2023. (查阅网上资料, 未找到对应的英文翻译, 请确认) Everbright Securities, Tang Jia-Rui, Tian Ran, Liang Dan-Hui. In-depth report on the E-commerce industry: Deepening online consumption mindset and actively exploring new consumption scenarios [Online], available: https://baijiahao.baidu.com/s?id=1760070652649669963&wfr=spider&for=pc, March 11, 2023. (查阅网上资料,未找到对应的英文翻译,请确认)
[2]	张洪磊, 李浥东, 邬俊, 陈乃月, 董海荣. 基于隐私保护的联邦推荐算法综述. 自动化学报, 2022, 48(9): 2142−2163 Zhang Hong-Lei, Li Yi-Dong, Wu Jun, Chen Nai-Yue, Dong Hai-Rong. A survey on privacy-preserving federated recommender systems. Acta Automatica Sinica, 2022, 48(9): 2142−2163
[3]	Yang Y, Zhang C B, Song X, Dong Z, Zhu H S, Li W J. Contextualized knowledge graph embedding for explainable talent training course recommendation. ACM Transactions on Information Systems, 2024, 42(2): Article No. 33
[4]	Cheng M Y, Liu Q, Zhang W Y, Liu Z D, Zhao H K, Chen E H. A general tail item representation enhancement framework for sequential recommendation. Frontiers of Computer Science, 2024, 18(6): Article No. 186333 doi: 10.1007/s11704-023-3112-y
[5]	Hao B W, Yin H Z, Li C P, Chen H. Self-supervised graph learning for occasional group recommendation. International Journal of Intelligent Systems, 2022, 37(12): 10880−10902 doi: 10.1002/int.23011
[6]	McCarthy J F, Anagnost T D. MusicFX: An arbiter of group preferences for computer supported collaborative workouts. In: Proceedings of the ACM Conference on Computer Supported Cooperative Work. Seattle Washington, USA: ACM, 1998. 363−372
[7]	许晓明, 梅红岩, 于恒, 李晓会. 基于偏好融合的群组推荐方法研究综述. 小型微型计算机系统, 2020, 41(12): 2500−2508 doi: 10.3969/j.issn.1000-1220.2020.12.008 Xu Xiao-Ming, Mei Hong-Yan, Yu Heng, Li Xiao-Hui. Review of group recommendation methods based on preference fusion. Journal of Chinese Computer Systems, 2020, 41(12): 2500−2508 doi: 10.3969/j.issn.1000-1220.2020.12.008
[8]	张玉洁, 杜雨露, 孟祥武. 组推荐系统及其应用研究. 计算机学报, 2016, 39(4): 745−764 doi: 10.11897/SP.J.1016.2016.00745 Zhang Yu-Jie, Du Yu-Lu, Meng Xiang-Wu. Research on group recommender systems and their applications. Chinese Journal of Computers, 2016, 39(4): 745−764 doi: 10.11897/SP.J.1016.2016.00745
[9]	赵海燕, 成若瑶, 陈庆奎, 曹健. 群组推荐系统: 现状与展望. 小型微型计算机系统, 2021, 42(6): 1144−1151 doi: 10.3969/j.issn.1000-1220.2021.06.004 Zhao Hai-Yan, Cheng Ruo-Yao, Chen Qing-Kui, Cao Jian. Group recommender system: Current status and future trends. Journal of Chinese Computer Systems, 2021, 42(6): 1144−1151 doi: 10.3969/j.issn.1000-1220.2021.06.004
[10]	Dara S, Ravindranath Chowdary C, Kumar C. A survey on group recommender systems. Journal of Intelligent Information Systems, 2020, 54(2): 271−295 doi: 10.1007/s10844-018-0542-3
[11]	Kompan M, Bielikova M. Group recommendations: Survey and perspectives. Computing and Informatics, 2014, 33(2): 446−476
[12]	O'Connor M, Cosley D, Konstan J A, Riedl J. PolyLens: A recommender system for groups of users. ECSCW 2001. Dordrecht: Springer, 2001. 199−218
[13]	Wu X X, Xiong Y, Zhang Y, Jiao Y Z, Zhang J W, Zhu Y Y, et al. ConsRec: Learning consensus behind interactions for group recommendation. In: Proceedings of the ACM Web Conference. Austin, USA: ACM, 2023. 240−250
[14]	Zhu R T, Lv D T, Yu Y, Zhu R H, Zheng Z Z, Bu K, et al. LINet: A location and intention-aware neural network for hotel group recommendation. In: Proceedings of the ACM Web Conference. Austin, USA: ACM, 2023. 779−789
[15]	Crossen A, Budzik J, Hammond K J. Flytrap: Intelligent group music recommendation. In: Proceedings of the 7th International Conference on Intelligent User Interfaces. San Francisco, USA: ACM, 2002. 184−185
[16]	Carroll J M, Rosson M B. Paradox of the active user. In: Proceedings of the Interfacing Thought: Cognitive Aspects of Human-computer Interaction. Cambridge, USA: MIT Press, 1987. 80−111
[17]	Zheng N, Li Q D, Liao S C, Zhang L M. Which photo groups should I choose? A comparative study of recommendation algorithms in Flickr. Journal of Information Science, 2010, 36(6): 733−750 doi: 10.1177/0165551510386164
[18]	Liu X J, Tian Y, Ye M, Lee W C. Exploring personal impact for group recommendation. In: Proceedings of the 21st ACM International Conference on Information and Knowledge Management. Maui, USA: ACM, 2012. 674−683
[19]	Yuan Q, Cong G, Lin C Y. COM: A generative model for group recommendation. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2014. 163−172
[20]	Wang Q, Mao Z D, Wang B, Guo L. Knowledge graph embedding: A survey of approaches and applications. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(12): 2724−2743 doi: 10.1109/TKDE.2017.2754499
[21]	Chen J W, Wu J K, Wu J C, Cao X Z, Zhou S, He X N. Adap-τ: Adaptively modulating embedding magnitude for recommendation. In: Proceedings of the ACM Web Conference. Austin, USA: ACM, 2023. 1085−1096
[22]	Dyer J S, Sarin R K. Group preference aggregation rules based on strength of preference. Management Science, 1979, 25(9): 822−832 doi: 10.1287/mnsc.25.9.822
[23]	吴云昌, 刘柏嵩, 王洋洋, 费晨杰. 群组推荐分析与研究综述. 电信科学, 2018, 34(12): 71−83 Wu Yun-Chang, Liu Bai-Song, Wang Yang-Yang, Fei Chen-Jie. Review of group recommendation analysis and research. Telecommunications Science, 2018, 34(12): 71−83
[24]	Garcia I, Pajares S, Sebastia L, Onaindia E. Preference elicitation techniques for group recommender systems. Information Sciences, 2012, 189: 155−175 doi: 10.1016/j.ins.2011.11.037
[25]	Masthoff J. Group recommender systems: Combining individual models. Recommender Systems Handbook. New York, USA: Springer, 2010. 677−702
[26]	Agarwal A, Chakraborty M, Ravindranath Chowdary C. Does order matter? Effect of order in group recommendation. Expert Systems With Applications, 2017, 82: 115−127 doi: 10.1016/j.eswa.2017.03.069
[27]	Baltrunas L, Makcinskas T, Ricci F. Group recommendations with rank aggregation and collaborative filtering. In: Proceedings of the 4th ACM Conference on Recommender Systems. Barcelona, Spain: ACM, 2010. 119−126
[28]	Yu Z W, Zhou X S, Hao Y B, Gu J H. TV program recommendation for multiple viewers based on user profile merging. User Modeling and User-Adapted Interaction, 2006, 16(1): 63−82 doi: 10.1007/s11257-006-9005-6
[29]	Xuan P C, Tang Y, Wang W S. Group recommendation method based on item type proportion factor. In: Proceedings of the IEEE/ACM International Conference on Utility and Cloud Computing Companion. Zurich, Switzerland: IEEE, 2018. 376−381
[30]	毛宇佳, 刘学军, 徐新艳, 张欣. 基于子组与社会行为的缩小群组推荐列表方法. 计算机科学, 2019, 46(2): 202−209 doi: 10.11896/j.issn.1002-137X.2019.02.031 Mao Yu-Jia, Liu Xue-Jun, Xu Xin-Yan, Zhang Xin. Method based on sub-group and social behavior for narrowing recommended list for groups. Computer Science, 2019, 46(2): 202−209 doi: 10.11896/j.issn.1002-137X.2019.02.031
[31]	Huang Z H, Xu X, Zhu H H, Zhou M C. An efficient group recommendation model with multiattention-based neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31(11): 4461−4474 doi: 10.1109/TNNLS.2019.2955567
[32]	Yin H Z, Wang Q Y, Zheng K, Li Z X, Yang J L, Zhou X F. Social influence-based group representation learning for group recommendation. In: Proceedings of the 35th International Conference on Data Engineering. Macao, China: IEEE, 2019. 566−577
[33]	Jameson A. More than the sum of its members: Challenges for group recommender systems. In: Proceedings of the Working Conference on Advanced Visual Interfaces. Gallipoli, Italy: ACM, 2004. 48−54
[34]	Du J, Li L, Gu P, Xie Q. A group recommendation approach based on neural network collaborative filtering. In: Proceedings of the 35th International Conference on Data Engineering Workshops. Macao, China: IEEE, 2019. 148−154
[35]	Quintarelli E, Rabosio E, Tanca L. Recommending new items to ephemeral groups using contextual user influence. In: Proceedings of the 10th ACM Conference on Recommender Systems. Boston, USA: USA, 2016. 285−292
[36]	Quijano-Sanchez L, Recio-Garcia J A, Diaz-Agudo B. Happymovie: A facebook application for recommending movies to groups. In: Proceedings of the 23rd International Conference on Tools with Artificial Intelligence. Boca Raton, USA: IEEE, 2011. 239−244
[37]	Quijano-Sánchez L, Recio-García J A, Díaz-Agudo B. Personality and social trust in group recommendations. In: Proceedings of the 22nd IEEE International Conference on Tools with Artificial Intelligence. Arras, France: IEEE, 2010. 121−126
[38]	Quijano-Sanchez L, Recio-Garcia J A, Diaz-Agudo B, Jimenez-Diaz G. Social factors in group recommender systems. ACM Transactions on Intelligent Systems and Technology (TIST), 2013, 4(1): Article No. 8
[39]	Hu L, Cao J, Xu G D, Cao L B, Gu Z P, Cao W. Deep modeling of group preferences for group-based recommendation. In: Proceedings of the 28th AAAI Conference on Artificial Intelligence. Québec City, Canada: AAAI, 2014. 1861−1867
[40]	Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. In: Proceedings of the 3rd International Conference on Learning Representations. San Diego, CA, USA: ICLR, 2015. 1−15
[41]	Pan X R, Ge C J, Lu R, Song S J, Chen G F, Huang Z Y, et al. On the integration of self-attention and convolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans, USA: IEEE, 2022. 805−815
[42]	Xu H T, Zhang J, Dai L R. Differential time-frequency log-mel spectrogram features for vision transformer based infant cry recognition. In: Proceedings of the Interspeech. Incheon, Korea: ISCA, 2022. 1963−1967
[43]	Ma Z Y, Li J J, Li G H, Cheng Y J. UniTranSeR: A unified transformer semantic representation framework for multimodal task-oriented dialog system. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. Dublin, Ireland: Association for Computational Linguistics, 2022. 103−114
[44]	郑建兴, 李沁文, 王素格, 李德玉. 融合属性偏好和多阶交互信息的可解释评分预测研究. 自动化学报, 2021, 48 (x): 1−14 (查阅网上资料,未能确认本条文献期号页码是否正确,请确认) Zheng Jian-Xing, Li Qin-Wen, Wang Su-Ge, Li De-Yu. Research on explainable rating prediction by fusing attribute preference and multi-order interaction information. Acta Automatica Sinica, 2021, 48 (x): 1−14
[45]	汤文兵, 任正云, 韩芳. 基于注意力机制的协同卷积动态推荐网络. 自动化学报, 2021, 47(10): 2438−2448 Tang Wen-Bing, Ren Zheng-Yun, Han Fang. Attention-based collaborative convolutional dynamic network for recommendation. Acta Automatica Sinica, 2021, 47(10): 2438−2448
[46]	Cao D, He X N, Miao L H, An Y H, Yang C, Hong R C. Attentive group recommendation. In: Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. Ann Arbor, USA: ACM, 2018. 645−654
[47]	Tran L V, Pham T A N, Tay Y, Liu Y D, Cong G, Li X L. Interact and decide: Medley of sub-attention networks for effective group recommendation. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. Paris, France: ACM, 2019. 255−264
[48]	He Z X, Chow C Y, Zhang J D, Li N. GRADI: Towards group recommendation using attentive dual top-down and bottom-up influences. In: Proceedings of the IEEE International Conference on Big Data. Los Angeles, USA: IEEE, 2019. 631−636
[49]	Zhang S, Zheng N, Wang D L. A novel attention-based global and local information fusion neural network for group recommendation. Machine Intelligence Research, 2022, 19(4): 331−346 doi: 10.1007/s11633-022-1336-1
[50]	McPherson M, Smith-Lovin L, Cook J M. Birds of a feather: Homophily in social networks. Annual Review of Sociology, 2001, 27: 415−444 doi: 10.1146/annurev.soc.27.1.415
[51]	Liang R X, Zhang Q, Wang J Q, Lu J. A hierarchical attention network for cross-domain group recommendation. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(3): 3859−3873 doi: 10.1109/TNNLS.2022.3200480
[52]	He Z X, Chow C Y, Zhang J D. GAME: Learning graphical and attentive multi-view embeddings for occasional group recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2020. 649−658 (查阅网上资料, 未找到出版地信息, 请补充) He Z X, Chow C Y, Zhang J D. GAME: Learning graphical and attentive multi-view embeddings for occasional group recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2020. 649−658 (查阅网上资料,未找到出版地信息,请补充)
[53]	Deng Z Y, Li C Y, Liu S J, Ali W, Shao J. Knowledge-aware group representation learning for group recommendation. In: Proceedings of the 37th International Conference on Data Engineering. Chania, Greece: IEEE, 2021. 1571−1582
[54]	Zhang S, Zheng N, Wang D L. HetGRec: Heterogeneous graph attention network for group recommendation. IEEE Intelligent Systems, 2023, 38(1): 9−18 doi: 10.1109/MIS.2022.3211074
[55]	Sankar A, Wu Y H, Wu Y H, Zhang W, Yang H, Sundaram H. Groupim: A mutual information maximization framework for neural group recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2020. 1279−1288 (查阅网上资料, 未找到出版地信息, 请补充) Sankar A, Wu Y H, Wu Y H, Zhang W, Yang H, Sundaram H. Groupim: A mutual information maximization framework for neural group recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2020. 1279−1288 (查阅网上资料,未找到出版地信息,请补充)
[56]	Veličković P, Fedus W, Hamilton W L, Liò P, Bengio Y, Hjelm R D. Deep graph infomax. In: Proceedings of the 7th International Conference on Learning Representations. New Orleans, USA: OpenReview.net, 2019. 1−17
[57]	Devlin J, Chang M W, Lee K, Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis, Minnesota: Association for Computational Linguistics, 2019. 4171−4186
[58]	Radford A, Narasimhan K, Salimans T, Sutskever H. Improving language understanding by generative pre-training. OpenAI. 2018. 1−12(查阅网上资料, 未能确认文献类型, 请确认)(查阅网上资料, 未能确认本条文献修改是否正确, 请确认) Radford A, Narasimhan K, Salimans T, Sutskever H. Improving language understanding by generative pre-training. OpenAI. 2018. 1−12 (查阅网上资料,未能确认文献类型,请确认) (查阅网上资料,未能确认本条文献修改是否正确,请确认)
[59]	Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. Language models are unsupervised multitask learners. OpenAI Blog, 2019, 1(8): 9
[60]	Zhang S, Zheng N, Wang D L. GBERT: Pre-training user representations for ephemeral group recommendation. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management. Atlanta, USA: ACM, 2022. 2631−2639
[61]	Zhang Y Y, Wu X, Fang Q, Qian S S, Xu C S. Knowledge-enhanced attributed multi-task learning for medicine recommendation. ACM Transactions on Information Systems, 2023, 41(1): Article No. 17
[62]	Cao D, He X N, Miao L H, Xiao G Y, Chen H, Xu J. Social-enhanced attentive group recommendation. IEEE Transactions on Knowledge and Data Engineering, 2021, 33(3): 1195−1209 doi: 10.1109/TKDE.2019.2936475
[63]	Yin H Z, Wang Q Y, Zheng K, Li Z X, Yang J L, Zhou X F. Social influence-based group representation learning for group recommendation. In: Proceedings of the 35th International Conference on Data Engineering. Macao, China: IEEE, 2019. 566−577 (查阅网上资料, 本条文献和第32条文献重复, 请核对) Yin H Z, Wang Q Y, Zheng K, Li Z X, Yang J L, Zhou X F. Social influence-based group representation learning for group recommendation. In: Proceedings of the 35th International Conference on Data Engineering. Macao, China: IEEE, 2019. 566−577 (查阅网上资料, 本条文献和第32条文献重复,请核对)
[64]	Yin H Z, Wang Q Y, Zheng K, Li Z X, Zhou X F. Overcoming data sparsity in group recommendation. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(7): 3447−3460
[65]	Chen H X, Yin H Z, Chen T, Nguyen Q V H, Peng W C, Li X. Exploiting centrality information with graph convolutions for network representation learning. In: Proceedings of the 35th International Conference on Data Engineering. Macao, China: IEEE, 2019. 590−601
[66]	He X N, Liao L Z, Zhang H W, Nie L Q, Hu X, Chua T S. Neural collaborative filtering. In: Proceedings of the 26th International Conference on World Wide Web. Perth, Australia: International World Wide Web Conferences Steering Committee, 2017. 173−182
[67]	Feng S S, Zhang H X, Wang L, Liu L, Xu Y C. Detecting the latent associations hidden in multi-source information for better group recommendation. Knowledge-Based Systems, 2019, 171: 56−68 doi: 10.1016/j.knosys.2019.02.002
[68]	Huang Z H, Xu X, Zhu H H, Zhou M C. An efficient group recommendation model with multiattention-based neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2020, 31 (11): 4461−4474 (查阅网上资料, 本条文献和第31条文献重复,请核对)
[69]	Choudhary N, Minz S, Bharadwaj K K. Negotiation framework for group recommendation based on fuzzy computational model of trust and distrust. Multimedia Tools and Applications, 2020, 79(37-38): 27337−27364 doi: 10.1007/s11042-020-09339-x
[70]	Guo L, Yin H Z, Wang Q Y, Cui B, Huang Z, Cui L Z. Group recommendation with latent voting mechanism. In: Proceedings of the 36th International Conference on Data Engineering. Dallas, USA: IEEE, 2020. 121−132
[71]	Guo L, Yin H Z, Chen T, Zhang X L, Zheng K. Hierarchical hyperedge embedding-based representation learning for group recommendation. ACM Transactions on Information Systems (TOIS), 2021, 40(1): Article No. 3
[72]	Seo Y D, Kim Y G, Lee E, Seol K S, Baik D K. An enhanced aggregation method considering deviations for a group recommendation. Expert Systems With Applications, 2018, 93: 299−312 doi: 10.1016/j.eswa.2017.10.027
[73]	Loveymi S, Hamzeh A. Proposing an evolutionary method based on maximization precision of group recommender systems. In: Proceedings of the 7th Conference on Information and Knowledge Technology. Urmia, Iran: IEEE, 2015. 1−6
[74]	Guo Z W, Tang C W, Tang H, Fu Y Q, Niu W J. A novel group recommendation mechanism from the perspective of preference distribution. IEEE Access, 2018, 6: 5865−5878 doi: 10.1109/ACCESS.2018.2792427
[75]	Sun Y Z, Han J W, Yan X F, Yu P S, Wu T Y. PathSim: Meta path-based top-k similarity search in heterogeneous information networks. Proceedings of the VLDB Endowment, 2011, 4(11): 992−1003 doi: 10.14778/3402707.3402736
[76]	Zeng Z N, Xiao C J, Yao Y, Xie R B, Liu Z Y, Lin F, et al. Knowledge transfer via pre-training for recommendation: A review and prospect. Frontiers in Big Data, 2021, 4: Article No. 602071 doi: 10.3389/fdata.2021.602071
[77]	Jafri S I H, Ghazali R, Javid I, Mahmood Z, Hassan A A A. Deep transfer learning with multimodal embedding to tackle cold-start and sparsity issues in recommendation system. PLoS One, 2022, 17(8):
[78]	Gan M X, Ma Y X. Knowledge transfer learning from multiple user activities to improve personalized recommendation. Soft Computing, 2022, 26(14): 6547−6566 doi: 10.1007/s00500-022-07178-6
[79]	Chen J W, Dong H D, Qiu Y, He X N, Xin X, Chen L, et al. AutoDebias: Learning to debias for recommendation. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2021. 21−30(查阅网上资料, 未找到出版地信息, 请补充) Chen J W, Dong H D, Qiu Y, He X N, Xin X, Chen L, et al. AutoDebias: Learning to debias for recommendation. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 2021. 21−30 (查阅网上资料,未找到出版地信息,请补充)
[80]	Chen J W, Dong H D, Wang X, Feng F L, Wang M, He X N. Bias and debias in recommender system: A survey and future directions. ACM Transactions on Information Systems, 2023, 41(3): Article No. 67
[81]	Chawla N V, Bowyer K W, Hall L O, Kegelmeyer W P. SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 2002, 16(1): 321−357
[82]	Mandal P, Samanta S, Pal M, Ranadive A S. Pythagorean linguistic preference relations and their applications to group decision making using group recommendations based on consistency matrices and feedback mechanism. International Journal of Intelligent Systems, 2020, 35(5): 826−849 doi: 10.1002/int.22226
[83]	Castro J, Quesada F J, Palomares I, Martínez L. A consensus-driven group recommender system. International Journal of Intelligent Systems, 2015, 30(8): 887−906 doi: 10.1002/int.21730
[84]	Garcia I, Sebastia L. A negotiation framework for heterogeneous group recommendation. Expert Systems With Applications, 2014, 41(4): 1245−1261 doi: 10.1016/j.eswa.2013.07.111
[85]	Xu Y S, Zhang Y X, Guo W, Guo H F, Tang R M, Coates M. GraphSAIL: Graph structure aware incremental learning for recommender systems. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management. ACM, 2020. 2861−2868(查阅网上资料, 未找到出版地信息, 请补充) Xu Y S, Zhang Y X, Guo W, Guo H F, Tang R M, Coates M. GraphSAIL: Graph structure aware incremental learning for recommender systems. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management. ACM, 2020. 2861−2868 (查阅网上资料,未找到出版地信息,请补充)
[86]	Song L Q, Tekin C, Van Der Schaar M. Online learning in large-scale contextual recommender systems. IEEE Transactions on Services Computing, 2016, 9(3): 433−445 doi: 10.1109/TSC.2014.2365795
[87]	Zheng N, Li Q D. A recommender system based on tag and time information for social tagging systems. Expert systems With Applications, 2011, 38(4): 4575−4587 doi: 10.1016/j.eswa.2010.09.131
[88]	Lin J H, Dai X Y, Xi Y J, Liu W W, Chen B, Li X Y, et al. How can recommender systems benefit from large language models: A survey. ACM Transactions on Information Systems, to be published, DOI: 10.1145/3678004.
[89]	Wu L K, Zheng Z, Qiu Z P, Wang H, Gu H C, Shen T J, et al. A survey on large language models for recommendation. World Wide Web, 2024, 27(5): Article No. 60 doi: 10.1007/s11280-024-01291-2
[90]	Li L, Zhang Y F, Liu D G, Chen L. Large language models for generative recommendation: A survey and visionary discussions. In: Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation. Torino, Italia: ELRA and ICCL, 2023. 10146−10159.
[91]	Qiu Z P, Wu X, Gao J Y, Fan W. U-BERT: Pre-training user representations for improved recommendation. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence. AAAI, 2021. 4320−4327(查阅网上资料, 未找到出版地信息, 请补充) Qiu Z P, Wu X, Gao J Y, Fan W. U-BERT: Pre-training user representations for improved recommendation. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence. AAAI, 2021. 4320−4327 (查阅网上资料,未找到出版地信息,请补充)