Movatterモバイル変換


[0]ホーム

URL:


Skip to main content

Advertisement

Springer Nature Link
Log in

Elaborating the Bayesian Priors in Unsupervised Graph Embedding via Graph Concepts

  • Conference paper
  • First Online:

Part of the book series:Lecture Notes in Computer Science ((LNAI,volume 12447))

Included in the following conference series:

  • 1529Accesses

Abstract

Unsupervised Graph Embedding yields specific importance because it performs well with inputs limited to the graph structure only. Proximity-preserving models, including link-preserving and Skip-Gram models, prove to be good approaches in both efficiency and accuracy on unsupervised tasks, even compared with state-of-the-art deep models. We first show that the optimization problem these models solve is equivalent to a Bayesian Inference problem, however, these models generally assume a uniform distribution for the target node representations, that is, the representations of nodes are not further constrained. In our paper, we elaborate this Bayesian prior resorting to potential concepts underlying a graph. These graph concepts can be communities in a graph, nodes with different interaction patterns et al. We further derive the optimization objective according to this elaborated prior, and proposed our learning objective. Intuitively, graph nodes of the same concept are embedded close to each other. Our paper proposes a flexible framework which is adaptable to any other proximity-based models. Experiments show that our model significantly elevates the baseline performances of proximity-preserving models, yielding state-of-the-art results on unsupervised learning tasks.

X. Ma and Z. Li—Equal Contribution.

This work was supported by the National Natural Science Foundation of China (Grant No. 61876006).

This is a preview of subscription content,log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 11439
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 14299
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Similar content being viewed by others

Notes

  1. 1.

    See Sect. 4. The same phenomenon is observed and noted in the appendix of GraphSAGE [6].

  2. 2.

    While Skip-Gram models including Deepwalk and node2vec [5] optimize a target embedding and a context embedding for each node, for convenience, we use one matrix\(\mathbf {U}\) to denote node embedding vectors following the first-order setup of [17]. Implementing\(\mathbf {U}\) with two different matrics does not influence the overall framework of our paper.

  3. 3.

    Set the same as [17] and [6].

  4. 4.

    Empirically, we divide\(O'_2\) by the representation dimensiond because\(O'_2\) is calculated through summing over all the elements in the representation vectors.

  5. 5.

    We choose Deepwalk as a representative of all Skip-Gram based models including node2vec [5]et al., of which the performance is evaluated analogous to Deepwalk and thus not shown.

  6. 6.

    The same parameters are set for Deepwalk baseline.

  7. 7.

    Macro f1s are not shown, in which a trend similar tomicro f1s is observed.

References

  1. Blondel, V.D., Guillaume, J.L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. J. Stat. Mech. Theor. Exp.2008(10), P10008 (2008)

    Article  Google Scholar 

  2. Bojchevski, A., Günnemann, S.: Deep Gaussian embedding of graphs: unsupervised inductive learning via ranking. arXiv preprinthttps://arxiv.org/abs/1707.03815 (2017)

  3. Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems, vol. 29, pp. 3844–3852 (2016)

    Google Scholar 

  4. Du, L., Lu, Z., Wang, Y., Song, G., Wang, Y., Chen, W.: Galaxy network embedding: a hierarchical community structure preserving approach. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018, pp. 2079–2085 (2018)

    Google Scholar 

  5. 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, KDD 2016, pp. 855–864. ACM (2016)

    Google Scholar 

  6. Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30, pp. 1024–1034 (2017)

    Google Scholar 

  7. Henaff, M., Bruna, J., LeCun, Y.: Deep convolutional networks on graph-structured data. arXiv preprinthttps://arxiv.org/abs/1506.05163 (2015)

  8. Huang, W., Zhang, T., Rong, Y., Huang, J.: Adaptive sampling towards fast graph representation learning. arXiv preprinthttps://arxiv.org/abs/1809.05343 (2018)

  9. Kipf, T.N., Welling, M.: Variational graph auto-encoders. In: Proceedings of NIPS Bayesian Deep Learning Workshop (2016)

    Google Scholar 

  10. Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th International Conference on Learning Representations, ICLR 2017 (2017)

    Google Scholar 

  11. Levy, O., Goldberg, Y.: Neural word embedding as implicit matrix factorization. In: Advances in Neural Information Processing Systems, vol. 27, pp. 2177–2185 (2014)

    Google Scholar 

  12. Li, Z., Zhang, L., Song, G.: GCN-LASE: Towards adequately incorporating link attributes in graph convolutional networks. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019 (2019)

    Google Scholar 

  13. Li, Z., Zhang, L., Song, G.: SepNE: Bringing separability to network embedding. In: Proceedings of the 33rd AAAI’s Conference on Artificial Intelligence, AAAI 2019 (2019)

    Google Scholar 

  14. Oh, S.J., Murphy, K., Pan, J., Roth, J., Schroff, F.: Modeling uncertainty with hedged instance embedding. arXiv preprinthttps://arxiv.org/abs/1810.00319 (2018)

  15. Perozzi, B., Al-Rfou, R., Skiena, S.: DeepWalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2014, pp. 701–710. ACM (2014)

    Google Scholar 

  16. Qiu, J., Dong, Y., Ma, H., Li, J., Wang, K., Tang, J.: Network embedding as matrix factorization: unifying DeepWalk, LINE, PTE, and node2vec. In: Proceedings of the 11th ACM International Conference on Web Search and Data Mining, WSDM 2018, pp. 459–467 (2018)

    Google Scholar 

  17. Tang, J., Qu, M., Zhang, M., Mei, Q.: LINE: Large-scale information network embedding. In: Proceedings of the 24th International Conference on World Wide Web, WWW 2015, pp. 1067–1077 (2015)

    Google Scholar 

  18. Lei, T., Jin, W., Barzilay, R., Jaakkola, T.: Deriving neural architectures from sequence and graph kernels. In: Proceedings of the 34th International Conference on Machine Learning, ICML 2017 (2017)

    Google Scholar 

  19. Tu, C., Zhang, W., Liu, Z., Sun, M.: Max-margin DeepWalk: discriminative learning of network representation. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence, IJCAI 2016 (2016)

    Google Scholar 

  20. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprinthttps://arxiv.org/abs/1710.10903 (2017)

  21. Wang, D., Cui, P., Zhu, W.: Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2016, pp. 1225–1234 (2016)

    Google Scholar 

  22. Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? In: Proceedings of the 7th International Conference on Learning Representations, ICLR 2019 (2019)

    Google Scholar 

  23. Yang, C., Liu, Z., Zhao, D., Sun, M., Chang, E.Y.: Network representation learning with rich text information. In: Proceedings of the 24th International Joint Conference on Artificial Intelligence, IJCAI 2015, pp. 2111–2117 (2015)

    Google Scholar 

  24. Yang, S., Li, L., Wang, S., Zhang, W., Huang, Q.: A graph regularized deep neural network for unsupervised image representation learning. In: Proceedings of IEEE Conference on Computer Vision & Pattern Recognition, CVPR 2017 (2017)

    Google Scholar 

  25. Zhu, D., Cui, P., Wang, D., Zhu, W.: Deep variational network embedding in Wasserstein space. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2018, pp. 2827–2836 (2018)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Key Laboratory of Machine Perception, Ministry of Education, Peking University, Beijing, China

    Xiaojun Ma & Guojie Song

  2. Center for Data Science, Peking University, Beijing, China

    Ziyao Li

  3. School of Electronics Engineering and Computer Science, Peking University, Beijing, China

    Siwei Wei

Authors
  1. Xiaojun Ma

    You can also search for this author inPubMed Google Scholar

  2. Ziyao Li

    You can also search for this author inPubMed Google Scholar

  3. Siwei Wei

    You can also search for this author inPubMed Google Scholar

  4. Guojie Song

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence toGuojie Song.

Editor information

Editors and Affiliations

  1. Northeastern University, Shenyang, China

    Xiaochun Yang

  2. School of Data and Computer Science, Guangzhou, China

    Chang-Dong Wang

  3. Griffith University, Southport, QLD, Australia

    Md. Saiful Islam

  4. School of Computer Science and Technology, Shenzhen, China

    Zheng Zhang

Rights and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ma, X., Li, Z., Wei, S., Song, G. (2020). Elaborating the Bayesian Priors in Unsupervised Graph Embedding via Graph Concepts. In: Yang, X., Wang, CD., Islam, M.S., Zhang, Z. (eds) Advanced Data Mining and Applications. ADMA 2020. Lecture Notes in Computer Science(), vol 12447. Springer, Cham. https://doi.org/10.1007/978-3-030-65390-3_15

Download citation

Publish with us

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 11439
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 14299
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only


[8]ページ先頭

©2009-2025 Movatter.jp