Journal of Computer Science and Technology ›› 2019, Vol. 34 ›› Issue (6): 1217-1229.doi: 10.1007/s11390-019-1971-3

Special Issue: Data Management and Data Mining

• Data Management and Data Mining • Previous Articles     Next Articles

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

Supplement

1

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] Dan-Hao Zhu, Xin-Yu Dai, Jia-Jun Chen. Pre-Train and Learn: Preserving Global Information for Graph Neural Networks [J]. Journal of Computer Science and Technology, 2021, 36(6): 1420-1430.
[2] Jia-Ke Ge, Yan-Feng Chai, Yun-Peng Chai. WATuning: A Workload-Aware Tuning System with Attention-Based Deep Reinforcement Learning [J]. Journal of Computer Science and Technology, 2021, 36(4): 741-761.
[3] Chen-Chen Sun, De-Rong Shen. Mixed Hierarchical Networks for Deep Entity Matching [J]. Journal of Computer Science and Technology, 2021, 36(4): 822-838.
[4] Yang Liu, Ruili He, Xiaoqian Lv, Wei Wang, Xin Sun, Shengping Zhang. Is It Easy to Recognize Baby's Age and Gender? [J]. Journal of Computer Science and Technology, 2021, 36(3): 508-519.
[5] Ying Li, Jia-Jie Xu, Peng-Peng Zhao, Jun-Hua Fang, Wei Chen, Lei Zhao. ATLRec: An Attentional Adversarial Transfer Learning Network for Cross-Domain Recommendation [J]. Journal of Computer Science and Technology, 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. Enriching Context Information for Entity Linking with Web Data [J]. Journal of Computer Science and Technology, 2020, 35(4): 724-738.
[7] Chao Kong, Bao-Xiang Chen, Li-Ping Zhang. DEM: Deep Entity Matching Across Heterogeneous Information Networks [J]. Journal of Computer Science and Technology, 2020, 35(4): 739-750.
[8] Yue Kou, De-Rong Shen, Dong Li, Tie-Zheng Nie, Ge Yu. Finding Communities by Decomposing and Embedding Heterogeneous Information Network [J]. Journal of Computer Science and Technology, 2020, 35(2): 320-337.
[9] Da-Wei Cheng, Yi Tu, Zhen-Wei Ma, Zhi-Bin Niu, Li-Qing Zhang. BHONEM: Binary High-Order Network Embedding Methods for Networked-Guarantee Loans [J]. Journal of Computer Science and Technology, 2019, 34(3): 657-669.
[10] Yifan Wu, Fan Yang, Yong Xu, Haibin Ling. Privacy-Protective-GAN for Privacy Preserving Face De-Identification [J]. Journal of Computer Science and Technology, 2019, 34(1): 47-60.
[11] Lei Guo, Yu-Fei Wen, Xin-Hua Wang. Exploiting Pre-Trained Network Embeddings for Recommendations in Social Networks [J]. , 2018, 33(4): 682-696.
[12] Huai-Yu Li, Wei-Ming Dong, Bao-Gang Hu. Facial Image Attributes Transformation via Conditional Recycle Generative Adversarial Networks [J]. , 2018, 33(3): 511-521.
[13] Sheng Zhang, Zhu-Zhong Qian, Jie Wu, Sang-Lu Lu. Service-Oriented Resource Allocation in Clouds: Pursuing Flexibility and Efficiency [J]. , 2015, 30(2): 421-436.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] Liu Mingye; Hong Enyu;. Some Covering Problems and Their Solutions in Automatic Logic Synthesis Systems[J]. , 1986, 1(2): 83 -92 .
[2] Chen Shihua;. On the Structure of (Weak) Inverses of an (Weakly) Invertible Finite Automaton[J]. , 1986, 1(3): 92 -100 .
[3] Gao Qingshi; Zhang Xiang; Yang Shufan; Chen Shuqing;. Vector Computer 757[J]. , 1986, 1(3): 1 -14 .
[4] Chen Zhaoxiong; Gao Qingshi;. A Substitution Based Model for the Implementation of PROLOG——The Design and Implementation of LPROLOG[J]. , 1986, 1(4): 17 -26 .
[5] Huang Heyan;. A Parallel Implementation Model of HPARLOG[J]. , 1986, 1(4): 27 -38 .
[6] Min Yinghua; Han Zhide;. A Built-in Test Pattern Generator[J]. , 1986, 1(4): 62 -74 .
[7] Tang Tonggao; Zhao Zhaokeng;. Stack Method in Program Semantics[J]. , 1987, 2(1): 51 -63 .
[8] Min Yinghua;. Easy Test Generation PLAs[J]. , 1987, 2(1): 72 -80 .
[9] Sun Yongqiang; Lu Ruzhan; Huang Xiaorong;. Termination Preserving Problem in the Transformation of Applicative Programs[J]. , 1987, 2(3): 191 -201 .
[10] Zhu Hong;. Some Mathematical Properties of the Functional Programming Language FP[J]. , 1987, 2(3): 202 -216 .

ISSN 1000-9000(Print)

         1860-4749(Online)
CN 11-2296/TP

 Home
Editorial Board
Author Guidelines
Subscription		 Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
Tel.:86-10-62610746
E-mail: jcst@ict.ac.cn
 
  Copyright ©2015 JCST, All Rights Reserved