Abstract
Network embedding based on the random walk and skip-gram model such as the DeepWalk and Node2Vec algorithms have received wide attention. We identify that these algorithms essentially estimate the node similarities by random walk simulation, which is unreliable, inefficient, and inflexible. We propose to explicitly use node similarity measures instead of random walk simulation. Based on this strategy and a new proposed similarity measure, we present a fast and scalable algorithm AA\(^{+}\)Emb. Experiments show that AA\(^{+}\)Emb outperforms state-of-the-art network embedding algorithms on several commonly used benchmark networks.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
A difference between DeepWalk and node2vec is that the former uses a pure random sampling strategy, while the latter introduces two hyper-parameters to use 2nd-order random walks in order to bias the walks towards a particular search strategy.
- 2.
DeepWalk originally uses hierarchical softmax [9] with an objective similar to this.
- 3.
We omitted evaluation in terms of Micro-F1 because the trends are basically similar to Macro-F1.
References
Adamic, L.A., Adar, E.: Friends and neighbors on the web. Soc. Netw. 25(3), 211–230 (2003)
Cai, H., Zheng, V.W., Chang, K.C.C.: A comprehensive survey of graph embedding: problems, techniques and applications. arXiv preprint arXiv:1709.07604 (2017)
Cao, S., Lu, W., Xu, Q.: GraRep: learning graph representations with global structural information. In: Proceedings of CIKM, pp. 891–900 (2015)
Goyal, P., Ferrara, E.: Graph embedding techniques, applications, and performance: a survey. arXiv preprint arXiv:1705.02801 (2017)
Grover, A., Leskovec, J.: node2vec: scalable feature learning for networks. In: Proceedings of KDD, pp. 855–864 (2016)
Hamilton, W.L., Ying, R., Leskovec, J.: Representation learning on graphs: methods and applications. arXiv preprint arXiv:1709.05584 (2017)
Lü, L., Medo, M., Yeung, C.H., Zhang, Y., Zhang, Z., Zhou, T.: Recommender systems. Phys. Rep. 519, 1–49 (2012)
Lü, L., Zhou, T.: Link prediction in complex networks: a survey. Physica A 390, 1150–1170 (2011)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of NIPS, pp. 3111–3119 (2013)
Ou, M., Cui, P., Pei, J., Zhang, Z., Zhu, W.: Asymmetric transitivity preserving graph embedding. In: Proceedings of KDD, pp. 1105–1114 (2016)
Perozzi, B., Al-Rfou, R., Skiena, S.: DeepWalk: online learning of social representations. In: Proceedings of KDD, pp. 701–710 (2014)
Ribeiro, L.F.R., Saverese, P.H.P., Figueiredo, D.R.: struc2vec: learning node representations from structural identity. In: Proceedings of KDD, pp. 385–394 (2017)
Tang, J., Qu, M., Mei, Q.: PTE: predictive text embedding through large-scale heterogeneous text networks. In: Proceedings of KDD, pp. 1165–1174 (2015)
Tang, J., et al.: Line: large-scale information network embedding. In: Proceedings of WWW, pp. 1067–1077 (2015)
Tang, L., Liu, H.: Relational learning via latent social dimensions. In: Proceedings of KDD, pp. 817–826 (2009)
Tang, L., Liu, H.: Scalable learning of collective behavior based on sparse social dimensions. In: Proceedings of CIKM, pp. 1107–1116 (2009)
Tsitsulin, A., Mottin, D., Karras, P., Müller, E.: Verse: versatile graph embeddings from similarity measures. In: Proceedings of WWW, pp. 539–548 (2018)
Wang, X., et al.: Community preserving network embedding. In: Proceedings of AAAI, pp. 203–209 (2017)
Yang, C., Sun, M., Liu, Z., Tu, C.: Fast network embedding enhancement via high order proximity approximation. In: Proceedings of IJCAI, pp. 3894–3900 (2017)
Yu, X., et al.: Personalized entity recommendation: a heterogeneous information network approach. In: Proceedings of WSDM, pp. 283–292 (2014)
Zhang, Y., Lyu, T., Zhang, Y.: Cosine: community-preserving social network embedding from information diffusion cascades. In: Proceedings of AAAI, pp. 2620–2627 (2018)
Acknowledgment
This paper is based on results obtained from a project commissioned by the New Energy and Industrial Technology Development Organization (NEDO).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, X., Kertkeidkachorn, N., Murata, T., Kim, KS., Leblay, J., Lynden, S. (2018). Network Embedding Based on a Quasi-Local Similarity Measure. In: Geng, X., Kang, BH. (eds) PRICAI 2018: Trends in Artificial Intelligence. PRICAI 2018. Lecture Notes in Computer Science(), vol 11012. Springer, Cham. https://doi.org/10.1007/978-3-319-97304-3_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-97304-3_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97303-6
Online ISBN: 978-3-319-97304-3
eBook Packages: Computer ScienceComputer Science (R0)