《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (12): 3654-3661.DOI: 10.11772/j.issn.1001-9081.2022121908
收稿日期:
2022-12-30
修回日期:
2023-03-23
接受日期:
2023-03-28
发布日期:
2023-04-07
出版日期:
2023-12-10
通讯作者:
朱宇
作者简介:
王可可(1999—),女,河南濮阳人,硕士研究生,主要研究方向:网络表示学习基金资助:
Keke WANG, Yu ZHU(), Xiaoying WANG, Jianqiang HUANG, Tengfei CAO
Received:
2022-12-30
Revised:
2023-03-23
Accepted:
2023-03-28
Online:
2023-04-07
Published:
2023-12-10
Contact:
Yu ZHU
About author:
WANG Keke, born in 1999, M. S. candidate. Her research interest is network representation learning.Supported by:
摘要:
与普通网络相比,超网络具有复杂的元组关系(超边),然而现有的大多数网络表示学习方法并不能捕获元组关系。针对上述问题,提出一种超边约束的异质超网络表示学习方法(HRHC)。首先,引入一种结合团扩展和星型扩展的方法,从而将异质超网络转换为异质网络;其次,引入感知节点语义相关性的元路径游走方法捕获异质节点之间的语义关系;最后,通过超边约束机制捕获节点之间的元组关系,从而获得高质量的节点表示向量。在3个真实世界的超网络数据集上的实验结果表明,对于链接预测任务,所提方法在drug、GPS和MovieLens数据集上都取得了较好的结果;对于超网络重建任务,当超边重建比率大于0.6时,所提方法在drug数据集上的准确性(ACC)优于次优的Hyper2vec(biased 2nd order random walks in Hyper-networks),同时所提方法在GPS数据集上的ACC超过其他基线方法中次优的基于关联图的超边超边约束的异质超网络表示学习方法(HRHC-关联图)15.6个百分点。
中图分类号:
王可可, 朱宇, 王晓英, 黄建强, 曹腾飞. 超边约束的异质超网络表示学习方法[J]. 计算机应用, 2023, 43(12): 3654-3661.
Keke WANG, Yu ZHU, Xiaoying WANG, Jianqiang HUANG, Tengfei CAO. Heterogeneous hypernetwork representation learning method with hyperedge constraint[J]. Journal of Computer Applications, 2023, 43(12): 3654-3661.
数据集 | 节点类型(节点数) | 边数 | ||
---|---|---|---|---|
drug | 用户(4) | 药物(132) | 反应(221) | 1 195 |
GPS | 用户(5) | 位置(70) | 活动(146) | 1 436 |
MovieLens | 用户(457) | 电影(1 688) | 标签(1 530) | 5 965 |
表1 数据集详情
Tab. 1 Dataset details
数据集 | 节点类型(节点数) | 边数 | ||
---|---|---|---|---|
drug | 用户(4) | 药物(132) | 反应(221) | 1 195 |
GPS | 用户(5) | 位置(70) | 活动(146) | 1 436 |
MovieLens | 用户(457) | 电影(1 688) | 标签(1 530) | 5 965 |
操作 | 符号 | 定义 |
---|---|---|
Weighted-L1 | ||
Weighted-L2 |
表2 二元算子
Tab. 2 Binary operator
操作 | 符号 | 定义 |
---|---|---|
Weighted-L1 | ||
Weighted-L2 |
二元算子 操作 | 方法 | drug数据集 | GPS数据集 | MovieLens数据集 | ||||||
---|---|---|---|---|---|---|---|---|---|---|
2-截图 | 关联图 | 2-截图+ 关联图 | 2-截图 | 关联图 | 2-截图+ 关联图 | 2-截图 | 关联图 | 2-截图+ 关联图 | ||
Weighted-L1 | DeepWalk | 79.12 | 88.32 | 88.91 | 85.40 | 87.21 | 90.58 | 69.20 | 89.06 | 90.54 |
node2vec | 78.54 | 88.18 | 88.61 | 82.99 | 88.14 | 90.92 | 71.36 | 88.76 | 90.33 | |
metapath2vec | 84.35 | 89.26 | 92.52 | 89.18 | 89.69 | 90.37 | 80.32 | 84.25 | 90.48 | |
CoarSAS2hvec | 86.02 | 88.14 | 91.53 | 88.14 | 91.92 | 94.85 | 93.60 | 94.77 | 96.34 | |
HRTC | 88.35 | 91.58 | 93.22 | 90.81 | 92.67 | 93.36 | 92.51 | 94.05 | 96.31 | |
HRHC | 87.92 | 90.46 | 93.01 | 87.46 | 92.67 | 92.78 | 93.14 | |||
Hyper2vec | 92.37 | 92.78 | 96.18 | |||||||
HPSG | 91.97 | 93.20 | 98.08 | |||||||
HPHG | 94.33 | 91.64 | ||||||||
Event2vec | 95.28 | 96.05 | 93.45 | |||||||
Weighted-L2 | DeepWalk | 77.08 | 89.05 | 87.45 | 85.22 | 88.69 | 90.06 | 68.77 | 88.86 | 90.63 |
node2vec | 77.96 | 88.47 | 88.48 | 83.85 | 86.43 | 91.12 | 70.37 | 89.27 | 91.26 | |
metapath2vec | 84.57 | 89.44 | 91.03 | 87.46 | 89.18 | 90.55 | 78.52 | 85.22 | 89.23 | |
CoarSAS2hvec | 87.08 | 88.77 | 92.80 | 87.80 | 92.61 | 92.07 | 94.14 | 95.31 | ||
HRTC | 87.08 | 91.84 | 94.27 | 90.47 | 92.53 | 93.39 | 91.18 | 93.47 | 95.54 | |
HRHC | 88.98 | 90.04 | 94.86 | 87.80 | 93.12 | 94.33 | 92.12 | 92.47 | ||
Hyper2vec | 93.43 | 91.92 | 95.82 | |||||||
HPSG | 92.14 | 93.12 | 97.80 | |||||||
HPHG | 95.83 | 93.47 | 91.38 | |||||||
Event2vec | 94.33 | 91.91 |
表3 链接预测的AUC比较 (%)
Tab. 3 AUC comparison of link prediction
二元算子 操作 | 方法 | drug数据集 | GPS数据集 | MovieLens数据集 | ||||||
---|---|---|---|---|---|---|---|---|---|---|
2-截图 | 关联图 | 2-截图+ 关联图 | 2-截图 | 关联图 | 2-截图+ 关联图 | 2-截图 | 关联图 | 2-截图+ 关联图 | ||
Weighted-L1 | DeepWalk | 79.12 | 88.32 | 88.91 | 85.40 | 87.21 | 90.58 | 69.20 | 89.06 | 90.54 |
node2vec | 78.54 | 88.18 | 88.61 | 82.99 | 88.14 | 90.92 | 71.36 | 88.76 | 90.33 | |
metapath2vec | 84.35 | 89.26 | 92.52 | 89.18 | 89.69 | 90.37 | 80.32 | 84.25 | 90.48 | |
CoarSAS2hvec | 86.02 | 88.14 | 91.53 | 88.14 | 91.92 | 94.85 | 93.60 | 94.77 | 96.34 | |
HRTC | 88.35 | 91.58 | 93.22 | 90.81 | 92.67 | 93.36 | 92.51 | 94.05 | 96.31 | |
HRHC | 87.92 | 90.46 | 93.01 | 87.46 | 92.67 | 92.78 | 93.14 | |||
Hyper2vec | 92.37 | 92.78 | 96.18 | |||||||
HPSG | 91.97 | 93.20 | 98.08 | |||||||
HPHG | 94.33 | 91.64 | ||||||||
Event2vec | 95.28 | 96.05 | 93.45 | |||||||
Weighted-L2 | DeepWalk | 77.08 | 89.05 | 87.45 | 85.22 | 88.69 | 90.06 | 68.77 | 88.86 | 90.63 |
node2vec | 77.96 | 88.47 | 88.48 | 83.85 | 86.43 | 91.12 | 70.37 | 89.27 | 91.26 | |
metapath2vec | 84.57 | 89.44 | 91.03 | 87.46 | 89.18 | 90.55 | 78.52 | 85.22 | 89.23 | |
CoarSAS2hvec | 87.08 | 88.77 | 92.80 | 87.80 | 92.61 | 92.07 | 94.14 | 95.31 | ||
HRTC | 87.08 | 91.84 | 94.27 | 90.47 | 92.53 | 93.39 | 91.18 | 93.47 | 95.54 | |
HRHC | 88.98 | 90.04 | 94.86 | 87.80 | 93.12 | 94.33 | 92.12 | 92.47 | ||
Hyper2vec | 93.43 | 91.92 | 95.82 | |||||||
HPSG | 92.14 | 93.12 | 97.80 | |||||||
HPHG | 95.83 | 93.47 | 91.38 | |||||||
Event2vec | 94.33 | 91.91 |
1 | ZHU Y, YE Z L, ZHAO H X, et al. Text-enhanced network representation learning [J]. Frontiers of Computer Science, 2020, 14(6): 146322. 10.1007/s11704-020-8440-6 |
2 | SHEIKH N, KEFATO Z T, MONTRESOR A. Semi-supervised heterogeneous information network embedding for node classification using 1D-CNN [C]// Proceedings of the 2018 Fifth International Conference on Social Networks Analysis, Management and Security. Piscataway: IEEE, 2018:177-181. 10.1109/snams.2018.8554840 |
3 | 刘昱阳,李龙杰,单娜,等.融合聚集系数的链接预测方法 [J]. 计算机应用, 2020, 40(1): 28-35. 10.11772/j.issn.1001-9081.2019061008 |
LIU Y Y, LI L J, SHAN N, et al. Link prediction method fusing clustering coefficients [J]. Journal of Computer Applications, 2020, 40(1): 28-35. 10.11772/j.issn.1001-9081.2019061008 | |
4 | 陈吉成,陈鸿昶.基于张量建模和进化K均值聚类的社区检测方法 [J]. 计算机应用, 2021, 41(11): 3120-3126. |
CHEN J C, CHEN H C. Community detection method based on tensor modeling and evolutionary K-means clustering [J]. Journal of Computer Applications, 2021, 41(11): 3120-3126. | |
5 | 胡秉德, 王新根, 王新宇, 等. 超图学习综述: 算法分类与应用分析[J]. 软件学报, 2022, 33(2): 498-523. |
HU B D, WANG X G, WANG X Y, et al. Survey on hypergraph learning: algorithm classification and application analysis [J]. Journal of Software, 2022, 33(2):498-523. | |
6 | AGARWAL S, BRANSON K, BELONGIE S. Higher order learning with graph [C]// Proceedings of the 23rd International Conference on Machine Learning. New York: ACM, 2006: 17-24. 10.1145/1143844.1143847 |
7 | FENG Y, YOU H, ZHANG Z, et al. Hypergraph neural networks [C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence and 31st Innovative Applications of Artificial Intelligence Conference and 9th AAAI Symposium on Educational Advances in Aritificial Intelligence. Palo Alto: AAAI Press, 2019: 3558-3565. 10.1609/aaai.v33i01.33013558 |
8 | HUANG J, CHEN C, YE F, et al. Hyper2vec: biased random walk for hyper-network embedding [C]// Proceedings of the 2019 International Conference on Database Systems for Advanced Applications. Cham: Springer, 2019: 273-277. 10.1007/978-3-030-18590-9_27 |
9 | TU K, CUI P, WANG F, et al. Structural deep embedding for hyper-networks [C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2018: 426-433. 10.1609/aaai.v32i1.11266 |
10 | ZHANG R, ZOU Y, MA J. Hyper-SAGNN: a self-attention based graph neural network for hypergraphs [EB/OL]. [2019-11-06]. . |
11 | JIANG J, WEI Y, FENG Y, et al. Dynamic hypergraph neural networks [C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2019: 2635-2641. 10.24963/ijcai.2019/366 |
12 | MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality [C]// Proceedings of the 26th International Conference on Neural Information Processing Systems. Palo Alto: AAAI Press, 2013,2: 3111-3119. |
13 | 刘贞国,朱宇,赵海兴,等.基于平移约束的异质超网络表示学习 [J]. 中文信息学报, 2022, 36(12): 74-84. 10.3969/j.issn.1003-0077.2022.12.008 |
LIU Z G, ZHU Y, ZHAO H X, et al. Heterogeneous hypernetwork representation learning with the translation constraint [J]. Journal of Chinese Information Processing, 2022, 36(12): 74-84. 10.3969/j.issn.1003-0077.2022.12.008 | |
14 | HONG S, ZHOU Z, ZIO E, et al. An adaptive method for health trend prediction of rotating bearings [J]. Digital Signal Processing, 2014, 35: 117-123. 10.1016/j.dsp.2014.08.006 |
15 | MATHIOUDALKIS M, KOUDAS N. TwitterMonitor: trend detection over the twitter stream [C]// Proceedings of the 29th ACM SIGMOD International Conference on Management of Data. New York: ACM, 2010: 1155-1158. 10.1145/1807167.1807306 |
16 | JANNACH D, ZANKER M, FELFERNIG A, et al. Recommender Systems: An Introduction [M]. New York: Cambridge University Press, 2010:1-10. 10.1017/cbo9780511763113 |
17 | BRETTO A. Hypergraph Theory: An Introduction [M]. Cham: Springer, 2013: 43-49. 10.1007/978-3-319-00080-0_3 |
18 | 刘贞国,朱宇,刘连照,等.基于转化策略的异质超网络表示学习[J].计算机应用研究, 2022, 39(11): 3333-3339. |
LIU Z G, ZHU Y, LIU L Z, et al. Heterogeneous hypernetwork representation learning with transformation strategy [J]. Application Research of Computers, 2022, 39(11): 3333-3339. | |
19 | BORDES A, USUNIER N, GARCIA-DURÁN A. Translating embeddings for modeling multi-relational data [C]// Proceedings of the 26th International Conference on Neural Information Processing Systems. Cham: Springer, 2013,2: 2787-2795. |
20 | ZHENG V W, CAO B, ZHENG Y, et al. Collaborative filtering meets mobile recommendation: a user-centered approach [C]// Proceedings of the 24th AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2010: 236-241. 10.1609/aaai.v24i1.7577 |
21 | HARPER F M, KONSTAN J A. The MovieLens datasets: history and context [J]. ACM Transactions on Internet and Information Systems, 2016, 5(4): 19. 10.1145/2827872 |
22 | PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk: online learning of social representations [C] // Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2014: 701-710. 10.1145/2623330.2623732 |
23 | 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. New York: ACM, 2016: 855-864. 10.1145/2939672.2939754 |
24 | 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. New York: ACM, 2017: 135-144. 10.1145/3097983.3098036 |
25 | ZHAN L, JIA T. CoarSAS2hvec: heterogeneous information network embedding with balanced network sampling [J]. Entropy, 2022, 24(2): 276. 10.3390/e24020276 |
26 | HUANG J, LIU X, SONG Y. Hyper-path-based representation learning for hyper-networks [C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management. New York: ACM, 2019: 449-458. 10.1145/3357384.3357871 |
27 | FU G, YUAN B, DUAN Q, et al. Representation learning for heterogeneous information networks via embedding events [C]// Proceedings of the 26th International Conference on Neural Information Processing Systems. Cham: Springer, 2019: 327-339. 10.1007/978-3-030-36708-4_27 |
28 | 杜航原,郝思聪,王文剑.结合图自编码器与聚类的半监督表示学习方法 [J]. 计算机应用, 2022, 42(9): 2643-2651. |
DU H Y, HAO S C, WANG W J. Semi-supervised representation learning method combining graph auto-encoder and clustering [J]. Journal of Computer Applications, 2022, 42(9): 2643-2651. |
[1] | 王静红, 周志霞, 王辉, 李昊康. 双路自编码器的属性网络表示学习[J]. 《计算机应用》唯一官方网站, 2023, 43(8): 2338-2344. |
[2] | 富坤, 郝玉涵, 孙明磊, 刘赢华. 基于优化图结构自编码器的网络表示学习[J]. 《计算机应用》唯一官方网站, 2023, 43(10): 3054-3061. |
[3] | 袁立宁, 刘钊. 基于One-Shot聚合自编码器的图表示学习[J]. 《计算机应用》唯一官方网站, 2023, 43(1): 8-14. |
[4] | 杜航原, 郝思聪, 王文剑. 结合图自编码器与聚类的半监督表示学习方法[J]. 《计算机应用》唯一官方网站, 2022, 42(9): 2643-2651. |
[5] | 余晓鹏, 何儒汉, 黄晋, 张俊杰, 胡新荣. 基于改进Inception结构的知识图谱嵌入模型[J]. 《计算机应用》唯一官方网站, 2022, 42(4): 1065-1071. |
[6] | 胡军, 许正康, 刘立, 钟福金. 融合多粒度社区信息的网络嵌入方法[J]. 《计算机应用》唯一官方网站, 2022, 42(3): 663-670. |
[7] | 富坤, 高金辉, 赵晓梦, 李佳宁. 融合全局结构信息的拓扑优化图卷积网络[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 357-364. |
[8] | 王高杰, 冶忠林, 赵海兴, 朱宇, 孟磊. 唐诗宋词中的超网络特性分析[J]. 计算机应用, 2021, 41(8): 2432-2439. |
[9] | 樊玮, 王慧敏, 邢艳. 基于自编码器的多视图属性网络表示学习模型[J]. 计算机应用, 2021, 41(4): 1064-1070. |
[10] | 李慧博, 赵云霄, 白亮. 基于深度神经网络和门控循环单元的动态图表示学习方法[J]. 《计算机应用》唯一官方网站, 2021, 41(12): 3432-3437. |
[11] | 刘昱阳, 李龙杰, 单娜, 陈晓云. 融合聚集系数的链接预测方法[J]. 计算机应用, 2020, 40(1): 28-35. |
[12] | 李瑶, 赵云芃, 李欣芸, 刘志芬, 陈俊杰, 郭浩. 基于sparse group Lasso方法的脑功能超网络构建与特征融合分析[J]. 计算机应用, 2020, 40(1): 62-70. |
[13] | 王文涛, 吴淋涛, 黄烨, 朱容波. 基于密集连接卷积神经网络的链路预测模型[J]. 计算机应用, 2019, 39(6): 1632-1638. |
[14] | 刘正铭, 马宏, 刘树新, 李海涛, 常圣. 融合节点描述属性信息的网络表示学习算法[J]. 计算机应用, 2019, 39(4): 1012-1020. |
[15] | 王文涛, 黄烨, 吴淋涛, 柯璇, 唐菀. 基于改进随机游走的网络表示学习算法[J]. 计算机应用, 2019, 39(3): 651-655. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||