采用新型元路径的异构图表示学习方法

doi:10.3778/j.issn.1673-9418.2202014

摘要/Abstract

摘要： 图神经网络已经成为推荐系统领域的一种主要方法。很多研究把元路径融入到异构图神经网络中，但绝大多数元路径的定义方式只考虑节点之间是否存在连接。而在异构图中同一个节点可能被多条不同类型的边所连接，如用户对物品的浏览、加入购物车、购买等不同交互行为，按照传统的元路径定义方式进行实例化会因为忽略了边的类型而导致学习的节点embedding不准确。针对上述问题，提出一种在异构图上把边类型融入到元路径的方法，使节点在每个场景下得到单独训练。然后，使用图注意力机制将不同场景下的同一节点的embedding进行聚合，最终得到该节点的embedding。并用来预测用户与未交互的物品之间的行为关系，从而达到向用户推荐物品的目的。实验表明，提出的算法在三个公开数据集上都取得了性能提升，在阿里天池赛数据集上[F1]、ROC-AUC和PR-AUC指标分别提高了8.75%、6.03%和4.86%。

关键词: 分布式表示, 异构图, 元路径, 推荐系统

Abstract: Graph neural network has become a main method in the field of recommendation system. Many studies integrate meta-path into heterogeneous graph neural network. However, most of the definitions of meta-paths only consider whether there is edge connection between nodes, but the same node may be connected by multiple different types of edges in the heterogeneous graph, such as users’ browsing, adding to the shopping cart, purchasing and other interactive behaviors. Then, instantiating according to the traditional definition method of meta-path can result in inaccurate embedding of nodes because the types of edge are ignored. To solve this problem, this paper proposes a method of integrating edge types into meta-paths in heterogeneous graphs, so that nodes can be trained indiv-idually in each scene. Then, the graph attention mechanism is used to aggregate the embedding of the same node in different scenes, and finally the embedding of the node is obtained. It is used to predict the behavioral relationship between users and non-interactive items, and then items are recommended to users. Experimental results show that the proposed algorithm improves the performance on three public datasets. In particular, the F1, ROC-AUC and PR-AUC scores are improved by 8.75%, 6.03% and 4.86% on Ali Tianchi Challenge dataset, respectively.

Key words: distributed representation, heterogeneous graph, meta-path, recommendation system

张程东, 王绍卿, 刘玉芳, 郑顺, 孙福振. 采用新型元路径的异构图表示学习方法[J]. 计算机科学与探索, 2023, 17(7): 1680-1689.

ZHANG Chengdong, WANG Shaoqing, LIU Yufang, ZHENG Shun, SUN Fuzhen. Method of Heterogeneous Graph Representation Learning Using Novel Meta-Path[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(7): 1680-1689.

参考文献

[1] 黄立威, 江碧涛, 吕守业, 等. 基于深度学习的推荐系统研究综述[J]. 计算机学报, 2018, 41(7): 1619-1647.
HUANG L W, JIANG B T, LV S Y, et al. Survey on deep learning based recommender systems[J]. Chinese Journal of Computers, 2018, 41(7): 1619-1647.
[2] 吴宾, 娄铮铮, 叶阳东. 一种面向多源异构数据的协同过滤推荐算法[J]. 计算机研究与发展, 2019, 56(5): 1034-1047.
WU B, LOU Z Z, YE Y D. A collaborative filtering recommendation algorithm for heterogeneous data[J]. Journal of Computer Research and Development, 2019, 56(5): 1034-1047.
[3] 尚燕敏, 曹亚男, 刘燕兵. 基于异构社交网络信息和内容信息的事件推荐[J]. 软件学报, 2020, 31(4): 1212-1224.
SHANG Y M, CAO Y N, LIU Y B. Based on hetero-geneous network information and content information of the event recommendation[J]. Journal of Software, 2020, 31(4): 1212-1224.
[4] 葛尧, 陈松灿. 面向推荐系统的图卷积网络[J]. 软件学报, 2020, 31(4): 1101-1112.
GE Y, CHEN S C. Recommendation system oriented graph convolution network[J]. Journal of Software, 2020, 31(4): 1101-1112.
[5] DONG Y, HU Z, WANG K, et al. Heterogeneous network representation learning[C]//Proceedings of the 29th Intern-ational Joint Conference on Artificial Intelligence, Yokoh-ama, Jan 7-15, 2021: 4861-4867.
[6] WANG X, JI H, SHI C, et al. Heterogeneous graph atten-tion network[C]//Proceedings of the World Wide Web Conference 2019, San Francisco, May 13-17, 2019. New York: ACM, 2019: 2022-2032.
[7] CHEN H, LI Y, SUN X, et al. Temporal meta-path guided explainable recommendation[C]//Proceedings of the 14th ACM International Conference on Web Search and Data Mining, Israel, Mar 8-12, 2021. New York: ACM, 2021: 1056-1064.
[8] 宋蕊, 李童, 董鑫, 等. 基于元路径嵌入的移动应用需求偏好分析方法[J]. 计算机研究与发展, 2021, 58(4): 749-762.
SONG R, LI T, DONG X, et al. Mobile application demand preference analysis method based on meta-path embedding[J]. Journal of Computer Research and Development, 2021, 58(4): 749-762.
[9] YANG H, CHEN H, LI L, et al. Hyper meta-path contras-tive learning for multi-behavior recommendation[C]//Proc-eedings of the 2021 IEEE International Conference on Data Mining, Auckland, Dec 7-10, 2021. Piscataway: IEEE, 2021: 787-796.
[10] ZHANG J, ZHU Y. Meta-path guided heterogeneous graph neural network for dish recommendation system[J]. Journal of Physics: Conference Series, 2021, 1883(1): 012102.
[11] LIU Y, YIN C, LI J, et al. Predicting dynamic user-item interaction with meta-path guided recursive RNN[J]. Algor-ithms, 2022, 15(3): 80.
[12] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv:1609.02907, 2016.
[13] HAMILTON W L, YING R, LESKOVEC J. Inductive repre- sentation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Proce-ssing Systems, Long Beach, Dec 4-9, 2017: 1025-1035.
[14] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. arXiv:1710.10903, 2017.
[15] PEROZZI B, AL-RFOU R, SKIENA S. Deepwalk: online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowle-dge Discovery and Data Mining, New York, Aug 24-27, 2014. New York: ACM, 2014: 701-710.
[16] GROVER A, LESKOVEC J. node2vec: scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, Aug 13-17, 2016. New York: ACM, 2016: 855-864.
[17] DONG Y, CHAWLA N V, SWAMI A. metapath2vec: scalable representation learning for heterogeneous networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, Aug 13-17, 2017. New York: ACM, 2017: 135-144.
[18] HE R, MCAULEY J. Ups and downs: modeling the visual evolution of fashion trends with one-class collaborative filt-ering[C]//proceedings of the 25th International Conference on World Wide Web, Montreal, Apr 11-15, 2016. New York: ACM, 2016: 507-517.
[19] TANG L, LIU H. Uncovering cross-dimension group stru-ctures in multi-dimensional networks[C]//Proceedings of the 2009 SDM Workshop on Analysis of Dynamic Net-works, 2009: 568-575.
[20] CEN Y, ZOU X, ZHANG J, et al. Representation learning for attributed multiplex heterogeneous network[C]//Proce-edings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Anchorage, Aug 4-8, 2019. New York: ACM, 2019: 1358-1368.
[21] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Proce-ssing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, Dec 4-9, 2017: 5998- 6008.