Text-enhanced network representation learning

Abstract

Network representation learning called NRL for short aims at embedding various networks into lowdimensional continuous distributed vector spaces. Most existing representation learning methods focus on learning representations purely based on the network topology, i.e., the linkage relationships between network nodes, but the nodes in lots of networks may contain rich text features, which are beneficial to network analysis tasks, such as node classification, link prediction and so on. In this paper, we propose a novel network representation learning model, which is named as Text-Enhanced Network Representation Learning called TENR for short, by introducing text features of the nodes to learn more discriminative network representations, which come from joint learning of both the network topology and text features, and include common influencing factors of both parties. In the experiments, we evaluate our proposed method and other baseline methods on the task of node classification. The experimental results demonstrate that our method outperforms other baseline methods on three real-world datasets.

Keywords

network representation / network topology / text features / joint learning

References

[1] Tsoumakas G, Katakis I. Multi-label classification: an overview. International Journal of Data Warehousing and Mining, 2007, 3(3): 1–13

[2] Tu C C, Liu Z Y, Sun M S. Inferring correspondences from multiple sources for microblog user tags. In: Proceedings of the 3rd Chinese National Conference on Social Media Processing. 2014, 1–12

[3] Yu H F, Jain P, Kar P, Dhillon I S. Large-scale multi-label learning with missing labels. In: Proceedings of the 31st International Conference on Machine Learning. 2014, 593–601

[4] Libennowell D, Kleinberg J M. The link-prediction problem for social networks. Journal of the Association for Information Science and Technology, 2007, 58(7): 1019–1031

[5] 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. 2014, 701–710

[6] 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. 2016, 855–864

[7] Tang J, Qu M, Wang M Z, Zhang M, Yan J, Mei Q Z. Line: large-scale information network embedding. In: Proceedings of the 24th International Conference on World Wide Web. 2015, 1067–1077

[8] Cao S S, Lu W, Xu Q K. Grarep: learning graph representations with global structural information. In: Proceedings of the 24th International Conference on Information and Knowledge Management. 2015, 891–900

[9] Wang D X, Cui P, Zhu W W. Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016, 1225–1234

[10] Chen H C, Perozzi B, Hu Y F, Skiena S. HARP: hierarchical representation learning for networks. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 2018, 2127–2134

[11] Yang C, Liu Z Y, Zhao D L, Sun M S, Chang E Y. Network representation learning with rich text information. In: Proceedings of the 24th International Joint Conference on Artificial Intelligence. 2015, 2111–2117

[12] Tu C C, Liu H, Liu Z Y, Sun M S. CANE: context-aware network embedding for relation modeling. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. 2017, 1722–1731

[13] Mikolov T, Sutskever I, Chen K, Corrado G, Dean J. Distributed representations of words and phrases and their compositionality. In: Proceedings of the 26th International Conference on Neural Information Processing Systems. 2013, 3111–3119

[14] Tu C C, Zhang W C, Liu Z Y, Sun M S. Max-Margin DeepWalk: discriminative learning of network representation. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. 2016, 3889–3895

[15] Tu C C, Zeng X K, Wang H, Zhang Z Y, Liu Z Y, Sun M S, Zhang B, Lin L Y. A unified framework for community detection and network representation learning. IEEE Transactions on Knowledge and Data Engineering, 2019, 31(6): 1051–1065

[16] Li C Z, Wang S Z, Yang D J, Li Z J, Yang Y, Zhang X M, Zhou J S. PPNE: property preserving network embedding. In: Proceedings of the 22nd International Conference on Database Systems for Advanced Applications. 2017, 163–179

[17] Yang D J, Wang S Z, Li C Z, Zhang X M, Li Z J. From properties to links: deep network embedding on incomplete graphs. In: Proceedings of the 26th ACM International Conference on Information and Knowledge Management. 2017, 367–376

[18] Sun X F, Guo J, Ding X, Liu T. A general framework for contentenhanced network representation learning. 2016, arXiv preprint arXiv:1610.02906

[19] Pan S R, Wu J, Zhu X Q, Zhang C Q, Wang Y. Tri-party deep network representation. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. 2016, 1895–1901

[20] Zhou H, Zhao Z Y, Li C, Liang Y Q, Zeng Q T. Rank2vec: learning node embeddings with local structure and global ranking. Expert Systems with Applications, 2019, 136: 276–287

[21] Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space. In: Proceedings of the 1st International Conference on Learning Representations. 2013

RIGHTS & PERMISSIONS

Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature