Abstract
Network representation learning based on neural network originates from language modeling based on neural network. These two types of tasks are then studied and applied along different paths. DeepWalk is the most classical network representation learning algorithm, which samples the next hop nodes of the walker with an equal probability method through the random walk strategy. Node2vec improves the random walk procedures, thus improving the performance of node2vec algorithm on various tasks. Therefore, we propose an improved DeepWalk algorithm based on preference random walk (PDW), which modifies the single undirected edge into two one-way directed edges in the network, and then gives each one-way directed edge a walk probability based on local random walk algorithm. In the procedures of acquiring walk sequences, the walk probability of the paths that have been walked will be attenuated according to the attenuation coefficient. For the last hop node of the current node in the walk sequences, an inhibition coefficient is set to prevent random walker from returning to the last node with a greater probability. In addition, we introduce the Alias sampling method in order to obtain the next hop node from the neighboring nodes of current node with a non-equal probability sampling. The experimental results show that the proposed PDW algorithm possesses a stable performance of network representation learning, the network node classification performance is better than that of the baseline algorithms used in this paper.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Vedanayaki, M.: A study of data mining and social network analysis. J. Test. Eval. 40(7), 663–681 (2014)
Bhat, S.Y., Abulaish, M.: Analysis and mining of online social networks: emerging trends and challenges. Wiley Interdisc. Rev. Data Min. Knowl. Discovery 3(6), 408–444 (2013)
Perozzi, B., Al-Rfou, R., Skiena, S., et al.: DeepWalk: online learning of social representations. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701–710. ACM, New York (2014)
Tu, C.C., Zhang, W.C., Liu, Z.Y., et al.: Max-margin DeepWalk: discriminative learning of network representation. In: International Joint Conference on Artificial Intelligence, pp. 3889–3895. AAAI, Palo Alto (2015)
Yang, C., Liu, Z.Y., Zhao, D., et al.: Network representation learning with rich text information. In: International Conference on Artificial Intelligence, pp. 2111–2117. AAAI, Palo Alto (2015)
Wang, D., Cui, P., Zhu, W., et al.: Structural deep network embedding. In: The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1225–1234. ACM, New York (2016)
Zhang, D., Jie, Y., Zhu, X., et al.: Network representation learning: a survey. IEEE Trans. Big Data PP(99), 1 (2017)
Li, W.J.: Predictive network representation learning for link prediction. http://101.96.10.64/www4.comp.polyu.edu.hk/~csztwang/paper/pnrl.pdf
Doncheva, N.T., Morris, J.H., Gorodkin, J., et al.: Cytoscape StringApp: network analysis and visualization of proteomics data. J. Proteome Res. 18(2), 623–632 (2019)
Zhao, W.X., Huang, J., Wen, J.-R.: Learning distributed representations for recommender systems with a network embedding approach. In: Ma, S., et al. (eds.) AIRS 2016. LNCS, vol. 9994, pp. 224–236. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-48051-0_17
Yu, X., Ren, X., Sun, Y.Z., et al.: Personalized entity recommendation: a heterogeneous information network approach. In: ACM International Conference on Web Search and Data Mining, pp. 283–292. ACM, New York (2014)
Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–864. ACM, New York (2016)
Ohata, F., Kondou, K., Inoue, K., et al.: Alias analysis method for object-oriented programs using alias flow graphs. Syst. Comput. Japan 35(4), 49–59 (2004)
Lai, S., Liu, K., He, S., et al.: How to generate a good word embedding. IEEE Intell. Syst. 31(6), 5–14 (2016)
Mikolov, T., Sutskever, I., Chen, K., et al.: Distributed representations of words and phrases and their compositionality. In: Twenty-Seventh Conference on Neural Information Processing System, pp. 3111–3119. MIT, Cambridge (2013)
Mikolov, T., Corrado, G., Chen, K., et al.: Efficient estimation of word representations in vector space. https://arxiv.org/abs/1301.3781
Kingman, J.F.C.: Markov transition probabilities. Zeitschrift Für Wahrscheinlichkeitstheorie Und Verwandte Gebiete 7(4), 248–270 (1967)
Liu, W., Lü, L.Y.: Link prediction based on local random walk. Europhys. Lett. 89(5), 58007 (2010)
Tang, J., Qu, M., Wang, M., et al.: LINE: large-scale information network embedding. In: International Conference on World Wide Web, pp. 1067–1077. Springer, Heidelberg (2014)
Chen, H., Perozzi, B., Hu, Y., et al.: HARP: hierarchical representation learning for networks. https://arxiv.org/abs/1706.07845
Yang, C., Sun, M., Liu, Z., et al.: Fast network embedding enhancement via high order proximity approximation. In: International Joint Conference on Artificial Intelligence, pp. 3894–3900. Morgan Kaufmann, San Francisco (2017)
Cao, S., Lu, W., Xu, Q., et al.: GraRep: learning graph representations with global structural information. In: Conference on Information and Knowledge Management, pp. 891–900. ACM, New York (2015)
Fan, R.E., Chang, K.W., Hsieh, C.J., et al.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9(9), 1871–1874 (2008)
Ye, Z., Zhao, H., Zhang, K., Zhu, Yu., Xiao, Y.: Text-associated max-margin DeepWalk. In: Xu, Z., Gao, X., Miao, Q., Zhang, Y., Bu, J. (eds.) Big Data 2018. CCIS, vol. 945, pp. 301–321. Springer, Singapore (2018). https://doi.org/10.1007/978-981-13-2922-7_21
Acknowledgement
This project is supported by NSFC (No. 11661069, 61663041 and 61763041).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Ye, Z., Zhao, H., Zhang, K., Zhu, Y., Xiao, Y., Wang, Z. (2019). Improved DeepWalk Algorithm Based on Preference Random Walk. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11838. Springer, Cham. https://doi.org/10.1007/978-3-030-32233-5_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-32233-5_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32232-8
Online ISBN: 978-3-030-32233-5
eBook Packages: Computer ScienceComputer Science (R0)
