计算机科学技术学报 ›› 2019,Vol. 34 ›› Issue (6): 1217-1229.doi: 10.1007/s11390-019-1971-3

所属专题： Data Management and Data Mining

• Data Management and Data Mining • 上一篇    下一篇

基于元路径注意力机制的异构网络对抗式嵌入

Chun-Yang Ruan1,2, Ye Wang3, Jiangang Ma4, Yanchun Zhang1,2,5, Xin-Tian Chen1,2   

  1. 1 Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai 200433, China;
    2 Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510006, China;
    3 College of Computer Science, National University of Defense Technology, Changsha 410073, China;
    4 School of Science, Engineering and Information Technology, Federation University Australia, Melbourne 3000, Australia;
    5 College of Engineering and Science, Victoria University, Melbourne 3000, Australia
  • 收稿日期:2019-01-23 修回日期:2019-09-24 出版日期:2019-11-16 发布日期:2019-11-16
  • 作者简介:Chun-Yang Ruan is a Ph.D. student at the School of Computer Science, Fudan University, Shanghai. He received his Master's degree in computer application from Zhengzhou University, Zhengzhou, in 2016. His main research interests include graph embedding and medical data mining.
  • 基金资助:
    This work was supported by the National Natural Science Foundation of China under Grant No. 61672161, and the Youth Research Fund of Shanghai Municipal Health and Family Planning Commission of China under Grant No. 2015Y0195.

Adversarial Heterogeneous Network Embedding with Metapath Attention Mechanism

Chun-Yang Ruan1,2, Ye Wang3, Jiangang Ma4, Yanchun Zhang1,2,5, Xin-Tian Chen1,2   

  1. 1 Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai 200433, China;
    2 Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510006, China;
    3 College of Computer Science, National University of Defense Technology, Changsha 410073, China;
    4 School of Science, Engineering and Information Technology, Federation University Australia, Melbourne 3000, Australia;
    5 College of Engineering and Science, Victoria University, Melbourne 3000, Australia
  • Received:2019-01-23 Revised:2019-09-24 Online:2019-11-16 Published:2019-11-16
  • About author:Chun-Yang Ruan is a Ph.D. student at the School of Computer Science, Fudan University, Shanghai. He received his Master's degree in computer application from Zhengzhou University, Zhengzhou, in 2016. His main research interests include graph embedding and medical data mining.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China under Grant No. 61672161, and the Youth Research Fund of Shanghai Municipal Health and Family Planning Commission of China under Grant No. 2015Y0195.

PDF (PC)

70

补充材料

1

异构信息网络（HIN）这种数据结构为解决现实中的数据挖掘任务提供了有效的模型。网络嵌入是基于网络的分析和预测任务的基础。目前流行的网络嵌入方法通常无法有效地保留HIN的语义信息。在本文研究中，我们提出了AGA2Vec，一种使用注意力机制和元路径的用于得到HIN嵌入的生成对抗模型。为了从多类型实体和对应关系中捕获语义信息，我们使用了一种加权元路径策略来保存HIN中节点的相似度。然后，我们使用自编码器和生成对抗模型来获得HIN的稳健表示。在几个真实世界数据集上的实验结果表明，我们所提出的方法优于最先进的HIN嵌入方法。

关键词: 异构信息网络, 网络嵌入, 注意力机制, 生成对抗网络

Abstract: Heterogeneous information network (HIN)-structured data provide an effective model for practical purposes in real world. Network embedding is fundamental for supporting the network-based analysis and prediction tasks. Methods of network embedding that are currently popular normally fail to effectively preserve the semantics of HIN. In this study, we propose AGA2Vec, a generative adversarial model for HIN embedding that uses attention mechanisms and meta-paths. To capture the semantic information from multi-typed entities and relations in HIN, we develop a weighted meta-path strategy to preserve the proximity of HIN. We then use an autoencoder and a generative adversarial model to obtain robust representations of HIN. The results of experiments on several real-world datasets show that the proposed approach outperforms state-of-the-art approaches for HIN embedding.

Key words: heterogeneous information network, network embedding, attention mechanism, generative adversarial network

[1] Chen Y X, Wang C G. HINE:Heterogeneous information network embedding. In Proc. the 22nd International Conference on Database Systems for Advanced Applications, March 2017, pp.180-195.
[2] Meng C P, Cheng R, Maniu S, Senellart P, Zhang W D. Discovering meta-paths in large heterogeneous information networks. In Proc. the 24th International Conference on World Wide Web, May 2015, pp.754-764.
[3] Shi C, Hu B B, Zhao X, Yu P. Heterogeneous information network embedding for recommendation. IEEE Transactions on Knowledge and Data Engineering, 2019, 31(2):357-370.
[4] Chen H X, Yin H Z, Wang W Q, Wang H, Nguyen Q V H, Li X. PME:Projected metric embedding on heterogeneous networks for link prediction. In Proc. the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, August 2018, pp.1177-1186.
[5] Fu T Y, Lee W C, Lei Z. HIN2Vec:Explore meta-paths in heterogeneous information networks for representation learning. In Proc. the 2017 ACM on Conference on Information and Knowledge Management, November 2017, pp.1797-1806.
[6] Wang H W, Zhang F Z, Hou M, Xie X, Guo M Y, Liu Q. SHINE:Signed heterogeneous information network embedding for sentiment link prediction. In Proc. the 11th ACM International Conference on Web Search and Data Mining, February 2018, pp.592-600.
[7] Shi Y, Gui H, Zhu Q, Kaplan L M, Han J W. AspEm:Embedding learning by aspects in heterogeneous information networks. In Proc. the 2018 SIAM International Conference on Data Mining, May 2018, pp.144-152.
[8] Dai Q Y, Li Q, Tang J, Wang D. Adversarial network embedding. In Proc. the 32nd AAAI Conference on Artificial Intelligence, February 2018, pp.2167-2174.
[9] Huang Z P, Mamoulis N. Heterogeneous information network embedding for meta path based proximity. arXiv:1701.05291, 2017. https://arxiv.org/pdf/17-01.05291.pdf, August 2019.
[10] Domhan T. How much attention do you need? A granular analysis of neural machine translation architectures. In Proc. the 56th Annual Meeting of the Association for Computational Linguistics, July 2018, pp.1799-1808.
[11] Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, WardeFarley D, Ozair S, Courville A C, Bengio Y. Generative adversarial nets. In Proc. the 2014 Annual Conference on Neural Information Processing Systems, December 2014, pp.2672-2680.
[12] Sun Y Z, Norick B, Han J W, Yan X F, Yu P S, Yu X. PathSelClus:Integrating meta-path selection with userguided object clustering in heterogeneous information networks. ACM Transactions on Knowledge Discovery from Data, 2013, 7(3):Article No. 11.
[13] Li J H, Wang C D, Huang L, Huang D, Lai J H, Chen P. Attributed network embedding with micro-meso structure. In Proc. the 23rd International Conference on Database Systems for Advanced Applications, May 2018, pp.20-36.
[14] Wang H W, Wang J, Wang J L, Zhao M, Zhang W N, Zhang F Z, Xie X, Guo M Y. GraphGAN:Graph representation learning with generative adversarial nets. In Proc. the 32nd AAAI Conference on Artificial Intelligence, February 2018, pp.2508-2515.
[15] Li C Z, Li Z J, Wang S Z, Yang Y, Zhang X M, Zhou J S. Semi-supervised network embedding. In Proc. the 22nd International Conference on Database Systems for Advanced Application, March 2017, pp.131-147.
[16] Tang J, Qu M, Wang M Z, Zhang M, Yan J, Mei Q Z. LINE:Large-scale information network embedding. In Proc. the 24th International Conference on World Wide Web, May 2015, pp.1067-1077.
[17] Grover A, Leskovec J. node2vec:Scalable feature learning for networks. In Proc. the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2016, pp.855-864.
[18] Cheng D W, Tu Y, Ma Z W, Niu Z B, Zhang L Q. BHONEM:Binary high-order network embedding methods for networked-guarantee loans. J. Comput. Sci. Technol., 2019, 34(3):657-669.
[19] Chang S Y, Han W, Tang J L, Qi G J, Aggarwal C C, Huang T S. Heterogeneous network embedding via deep architectures. In Proc. the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2015, pp.119-128.
[20] Guo L, Wen Y F, Wang X H. Exploiting pre-trained network embeddings for recommendations in social networks. J. Comput. Sci. Technol., 2018, 33(4):682-696.
[21] Zhou D F, Fan J X, Lin C K, Cheng B L, Zhou J Y, Liu Z. Optimal path embedding in the exchanged crossed cube. J. Comput. Sci. Technol., 2017, 32(3):618-629.
[22] Dong Y X, Chawla N V, Swami A. Metapath2vec:Scalable representation learning for heterogeneous networks. In Proc. the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2017, pp.135-144.
[23] Ji H Y, Shi C, Wang B. Attention based meta path fusion for heterogeneous information network embedding. In Proc. the 15th Pacific Rim International Conference on Artificial Intelligence, August 2018, pp.348-360.
[24] Wang X, Ji H Y, Shi C, Wang B, Ye Y F, Cui P, Yu P S. Heterogeneous graph attention network. In Proc. the 2019 World Wide Web Conference, May 2019, pp.2022-2032.
[25] Fang Y, Lin W Q, Zheng V W C, Wu M, Chang K C C, Li X L. Semantic proximity search on graphs with metagraph-based learning. In Proc. the 32nd IEEE International Conference on Data Engineering, May 2016, pp.277-288.
[26] Zhang D K, Yin J, Zhu X G, Zhang C Q. Metagraph2vec:Complex semantic path augmented heterogeneous network embedding. In Proc. the 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining, June 2018, pp.196-208.
[27] Sun L C, He L F, Huang Z P, Cao B K, Xia C Y, Wei X K, Yu P S. Joint embedding of meta-path and meta-graph for heterogeneous information networks. In Proc. the 2018 IEEE International Conference on Big Knowledge, November 2018, pp.131-138.
[28] Donahue J, Krähenbühl P, Darrell T. Adversarial feature learning. In Proc. the 5th International Conference on Learning Representations, April 2017.
[29] Bousmalis K, Silberman N, Dohan D, Erhan D, Krishnan D. Unsupervised pixel-level domain adaptation with generative adversarial networks. In Proc. the 2017 IEEE Conference on Computer Vision and Pattern Recognition, July 2017, pp.95-104.
[30] Li H Y, Dong W M, Hu B G. Facial image attributes transformation via conditional recycle generative adversarial networks. J. Comput. Sci. Technol., 2018, 33(3):511-521.
[31] Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks. In Proc. the 4th International Conference on Learning Representations, May 2016.
[32] Xiao Y, Xiao D, Hu B B, Shi C. ANE:Network embedding via adversarial autoencoders. In Proc. the 2018 IEEE International Conference on Big Data and Smart Computing, January 2018, pp.66-73.
[33] Wang D X, Cui P, Zhu W W. Structural deep network embedding. In Proc. the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2016, pp.1225-1234.
[34] Gulrajani I, Ahmed Fa, Arjovsky M, Dumoulin V, Courville A C. Improved training of Wasserstein GANs. In Proc. the 2017 Annual Conference on Neural Information Processing Systems, December 2017, pp.5769-5779.
[35] 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.
[36] Perozzi B, Al-Rfou' R, Skiena S. DeepWalk:Online learning of social representations. In Proc. the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2014, pp.701-710.
[37] Tang J, Zhang J, Yao L M, Li J Z, Zhang L, Su Z. ArnetMiner:Extraction and mining of academic social networks. In Proc. the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2008, pp.990-998.
[1] Jia-Ke Ge, Yan-Feng Chai, Yun-Peng Chai. WATuning：一种基于注意力机制的深度强化学习的工作负载感知调优系统[J]. 计算机科学技术学报, 2021, 36(4): 741-761.
[2] Chen-Chen Sun, De-Rong Shen. 面向深度实体匹配的混合层次网络[J]. 计算机科学技术学报, 2021, 36(4): 822-838.
[3] Sheng-Luan Hou, Xi-Kun Huang, Chao-Qun Fei, Shu-Han Zhang, Yang-Yang Li, Qi-Lin Sun, Chuan-Qing Wang. 基于深度学习的文本摘要研究综述[J]. 计算机科学技术学报, 2021, 36(3): 633-663.
[4] Yang Liu, Ruili He, Xiaoqian Lv, Wei Wang, Xin Sun, Shengping Zhang. 婴儿的年龄和性别容易被识别吗？[J]. 计算机科学技术学报, 2021, 36(3): 508-519.
[5] Ying Li, Jia-Jie Xu, Peng-Peng Zhao, Jun-Hua Fang, Wei Chen, Lei Zhao. ATLRec:用于跨领域推荐的注意力对抗迁移学习网络[J]. 计算机科学技术学报, 2020, 35(4): 794-808.
[6] Yi-Ting Wang, Jie Shen, Zhi-Xu Li, Qiang Yang, An Liu, Peng-Peng Zhao, Jia-Jie Xu, Lei Zhao, Xun-Jie Yang. 基于搜索引擎丰富上下文信息的实体链接方法[J]. 计算机科学技术学报, 2020, 35(4): 724-738.
[7] Chao Kong, Bao-Xiang Chen, Li-Ping Zhang. 跨异构信息网络的深度实体匹配[J]. 计算机科学技术学报, 2020, 35(4): 739-750.
[8] Huan-Jing Yue, Sheng Shen, Jing-Yu Yang, Hao-Feng Hu, Yan-Fang Chen. 基于渐进式通道注意力网络的参考图引导超分辨率研究[J]. 计算机科学技术学报, 2020, 35(3): 551-563.
[9] Yue Kou, De-Rong Shen, Dong Li, Tie-Zheng Nie, Ge Yu. 基于异构信息网络分解与嵌入的社区发现方法[J]. 计算机科学技术学报, 2020, 35(2): 320-337.
[10] Da-Wei Cheng, Yi Tu, Zhen-Wei Ma, Zhi-Bin Niu, Li-Qing Zhang. 二元高阶担保网络表示学习方法[J]. 计算机科学技术学报, 2019, 34(3): 657-669.
[11] Lei Guo, Yu-Fei Wen, Xin-Hua Wang. 社会网络中基于预训练网络嵌入式表示模型的推荐算法研究[J]. , 2018, 33(4): 682-696.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 刘明业; 洪恩宇;. Some Covering Problems and Their Solutions in Automatic Logic Synthesis Systems[J]. , 1986, 1(2): 83 -92 .
[2] 陈世华;. On the Structure of (Weak) Inverses of an (Weakly) Invertible Finite Automaton[J]. , 1986, 1(3): 92 -100 .
[3] 高庆狮; 张祥; 杨树范; 陈树清;. Vector Computer 757[J]. , 1986, 1(3): 1 -14 .
[4] 陈肇雄; 高庆狮;. A Substitution Based Model for the Implementation of PROLOG——The Design and Implementation of LPROLOG[J]. , 1986, 1(4): 17 -26 .
[5] 黄河燕;. A Parallel Implementation Model of HPARLOG[J]. , 1986, 1(4): 27 -38 .
[6] 闵应骅; 韩智德;. A Built-in Test Pattern Generator[J]. , 1986, 1(4): 62 -74 .
[7] 唐同诰; 招兆铿;. Stack Method in Program Semantics[J]. , 1987, 2(1): 51 -63 .
[8] 闵应骅;. Easy Test Generation PLAs[J]. , 1987, 2(1): 72 -80 .
[9] 孙永强; 陆汝占; 黄小戎;. Termination Preserving Problem in the Transformation of Applicative Programs[J]. , 1987, 2(3): 191 -201 .
[10] 朱鸿;. Some Mathematical Properties of the Functional Programming Language FP[J]. , 1987, 2(3): 202 -216 .
版权所有 © 《计算机科学技术学报》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持：support@magtech.com.cn
总访问量：