随着社交媒体的普及,人们逐渐将研究方向从个人推荐算法转移到群组推荐算法,现有的群组推荐模型大多采用启发式或基于注意力的偏好聚合策略聚合群组成员的个人偏好形成群组偏好。然而,由于用户交互数据的稀疏性,学习后的用户特征并不完备,现实生活中用户的交互非常复杂,而且用户关系有可能是高阶的;再者,群组之间的相似性和群组间共同成员的个人偏好经常被忽视,而群组相似性的学习对于提高群组表征学习具有很大的潜力。针对上述问题,该文设计了一种融合超图卷积和自监督协同训练的组推荐算法(HCSC)。首先,在用户级超图中,利用三个通道编码超图卷积网络中的高阶用户关系,通过聚合多个通道学习的用户特征,获得增强的用户表示,这为学习群组偏好提供了坚实的基础。其次,在组级超图中,将所有的群组连接为重叠网络,并关注群组共同成员的个人偏好,其超边嵌入过程可视为对群组偏好的学习。为进一步增强群组表示,将自监督学习和协同训练相结合,在上述两个超图上构建两个不同的图编码器,递归地利用不同信息生成标注样本,通过对比学习策略互相监督,与丢弃策略相比,所提出的自监督协同训练保留了完整信息,实现了真正的数据增强。该文提出的HCSC模型在两个真实世界的数据集上进行了广泛的实验,实验结果证明了该文提出的HCSC模型的优越性。
Abstract
With the popularity of social media, people are gradually shifting their research direction from individual recommendation algorithms to group recommendation algorithms. Most existing group recommendation models use heuristic or attention-based preference aggregation strategies to aggregate the individual preferences of group members to form group preferences. To further improve this task, this paper presents a group recommendation algorithm (HCSC) that incorporates hypergraph convolution and self-supervised collaborative training. First, in the user-level hypergraph, three channels are used to encode higher-order user relationships in the hypergraph convolutional network to enhance user representation by aggregating user features learned from multiple channels. Secondly, in group-level hypergraphs, all groups are connected as overlapping networks and the attention is paid to the individual preferences of common group members, in which the process of hyperedge embedding can be considered as the learning of group preferences. Thirdly, to further enhance the cluster representation, self-supervised learning and co-training are combined to construct two different graph encoders on the above two hypergraphs, recursively using annotated samples generated from different information to supervise each other through comparative learning, and the proposed self-supervised co-training retains complete information and achieves true data enhancement compared to the discard strategy. Experiments on two real-world datasets demonstrate the superiority of the proposed HCSC model in this paper.
关键词
群组推荐 /
超图卷积 /
自监督学习 /
协同训练 /
对比学习
{{custom_keyword}} /
Key words
group recommendation /
hypergraph convolution /
self-supervised learning /
co-training /
contrast learning
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] HU Y, MANIKONDA L, KAMBHAMPATI S. What we instagram: A first analysis of instagram photo content and user types[C]//Proceedings of the 8th International AAAI Conference on Weblogs and Social Media, 2014: 595-598.
[2] WILSON R E, GOSLING S D, GRAHAM L T. A review of Facebook research in the social sciences[J]. Perspectives on Psychological Science, 2012, 7(3): 203-220.
[3] PALLA G, BARABSI A L, VICSEK T. Quantifying social group evolution[J]. Nature, 2007, 446(7136): 664-667.
[4] WANG P, LI L, WANG R, et al. Socially-driven multi-interaction attentive group representation learning for group recommendation[J]. Pattern Recognition Letters, 2021, 145: 74-80.
[5] CAO D, HE X, MIAO L, et al. Social-enhanced attentive group recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 33(3): 1195-1209.
[6] VINH TRAN L, NGUYEN PHAM T A, TAY Y, et al. Interact and decide: Medley of sub-attention networks for effective group recommendation[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019: 255-264.
[7] GUO L, YIN H, CHEN T, et al. Hierarchical hyperedge embedding-based representation learning for group recommendation[J]. ACM Transactions on Information Systems, 2021, 40(1): 1-27.
[8] HE X, DENG K, WANG X, et al. Lightgcn: Simplifying and powering graph convolution network for recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020: 639-648.
[9] BALTRUNAS L, MAKCINSKAS T, RICCI F. Group recommendations with rank aggregation and collaborative filtering[C]//Proceedings of the 4th ACM Conference on Recommender Systems, 2010: 119-126.
[10] GUO L, YIN H, WANG Q, et al. Group recommendation with latent voting mechanism[C]//Proceedings of the 36th International Conference on Data Engineering. IEEE, 2020: 121-132.
[11] YIN H, WANG Q, ZHENG K, et al. Overcoming data sparsity in group recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34(7): 3447-3460.
[12] CAO D, HE X, MIAO L, et al. Attentive group recommendation[C]//Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, 2018: 645-654.
[13] 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, 29(10): 3164-3183.
[14] WU Z, PAN S, CHEN F, et al. A comprehensive survey on graph neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(1): 4-24.
[15] FAN W, MA Y, LI Q, et al. Graph neural networks for social recommendation[C]//Proceedings of the World Wide Web Conference, 2019: 417-426.
[16] WANG L, EGOROVA E K, MOKRYAKOV A V. Development of hypergraph theory[J]. Journal of Computer and Systems Sciences International, 2018, 57(1): 109-114.
[17] FENG Y, YOU H, ZHANG Z, et al. Hypergraph neural networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence,2019,33(01): 3558-3565.
[18] KIM E S, KANG W Y, ON K W, et al. Hypergraph attention networks for multimodal learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 14581-14590.
[19] BU J, TAN S, CHEN C, et al. Music recommendation by unified hypergraph: Combining social media information and music content[C]//Proceedings of the 18th ACM International Conference on Multimedia. 2010: 391-400.
[20] ZHENG X, LUO Y, SUN L, et al. A novel social network hybrid recommender system based on hypergraph topologic structure[J]. World Wide Web, 2018, 21(4): 985-1013.
[21] YANG D, QU B, YANG J, et al. Revisiting user mobility and social relationships in LBSNS: A hypergraph embedding approach[C]//Proceedings of the World Wide Web Conference, 2019: 2147-2157.
[22] YIN H, WANG Q, ZHENG K, et al. Social influence-based group representation learning for group recommendation[C]//Proceedings of the 35th International Conference on Data Engineering. IEEE, 2019: 566-577.
[23] SANKAR A, WU Y, WU Y, et al. GroupIM: A mutual information maximization framework for neural group recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020: 1279-1288.
[24] DOERSCH C, GUPTA A, EFROS A A. Unsupervised visual representation learning by context prediction[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1422-1430.
[25] PENG Z, HUANG W, LUO M, et al. Graph representation learning via graphical mutual information maximization[C]//Proceedings of the Web Conference, 2020: 259-270.
[26] XIE X, SUN F, LIU Z, et al. Contrastive pre-training for sequential recommendation[J]. arXiv e-prints, 2020: arXiv: 2010.14395,2020.
[27] DA COSTA A F, MANZATO M G, CAMPELLO R J G B. CoRec: A co-training approach for recommender systems[C]//Proceedings of the 33rd Annual ACM Symposium on Applied Computing, 2018: 696-703.
[28] BLUM A, MITCHELL T. Combining labeled and unlabeled data with co-training[C]//Proceedings of the 11th Annual Conference on Computational Learning Theory, 1998: 92-100.
[29] HAN T, XIE W, ZISSERMAN A. Self-supervised co-training for video representation learning[J]. Advances in Neural Information Processing Systems, 2020, 33: 5679-5690.
[30] ZHANG J, GAO M, YU J, et al. Double-scale self-supervised hypergraph learning for group recommendation[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 2021: 2557-2567
[31] YU J, YIN H, LI J, et al. Self-supervised multi-channel hypergraph convolutional network for social recommendation[C]//Proceedings of the Web Conference, 2021: 413-424.
[32] CREMONESI P, KOREN Y, TURRIN R. Performance of recommender algorithms on top-n recommendation tasks[C]//Proceedings of the 4th ACM Conference on Recommender Systems, 2010: 39-46.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61972182)
{{custom_fund}}
PDF(1713 KB)
