Abstract
We propose a novel approach for learning node representations in directed graphs, which maintains separate views or embedding spaces for the two distinct node roles induced by the directionality of the edges. We argue that the previous approaches either fail to encode the edge directionality or their encodings cannot be generalized across tasks. With our simple alternating random walk strategy, we generate role specific vertex neighborhoods and train node embeddings in their corresponding source/target roles while fully exploiting the semantics of directed graphs. We also unearth the limitations of evaluations on directed graphs in previous works and propose a clear strategy for evaluating link prediction and graph reconstruction in directed graphs. We conduct extensive experiments to showcase our effectiveness on several real-world datasets on link prediction, node classification and graph reconstruction tasks. We show that the embeddings from our approach are indeed robust, generalizable and well performing across multiple kinds of tasks and graphs. We show that we consistently outperform all baselines for node classification task. In addition to providing a theoretical interpretation of our method we also show that we are considerably more robust than the other directed graph approaches.
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
Notes
- 1.
We make available our implementation with corresponding data at https://git.l3s.uni-hannover.de/khosla/nerd.
References
Abu-El-Haija, S., Perozzi, B., Al-Rfou, R.: Learning edge representations via low-rank asymmetric projections. In: CIKM 2017, pp. 1787–1796 (2017)
Ammann, L.P.: Robust singular value decompositions: a new approach to projection pursuit. J. Am. Stat. Assoc. 88(422), 505–514 (1993)
Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. Adv. Neural Inf. Process. Syst. 14, 585–591 (2002)
Cao, S., Lu, W., Xu, Q.: GraRep: learning graph representations with global structural information. In: CIKM 2015, pp. 891–900 (2015)
Cao, S., Lu, W., Xu, Q.: Deep neural networks for learning graph representations. In: Proceedings of AAAI, AAAI 2016, pp. 1145–1152 (2016)
Chen, M., Yang, Q., Tang, X.: Directed graph embedding. In: IJCAI (2007)
Drobyshevskiy, M., Korshunov, A., Turdakov, D.: Learning and scaling directed networks via graph embedding. In: Ceci, M., Hollmén, J., Todorovski, L., Vens, C., Džeroski, S. (eds.) ECML PKDD 2017. LNCS (LNAI), vol. 10534, pp. 634–650. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71249-9_38
Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: KDD, pp. 855–864 (2016)
Katz, L.: A new status index derived from sociometric analysis. Psychometrika 18(1), 39–43 (1953)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. In: NeurIPS Workshop on Bayesian Deep Learning (NeurIPS-16 BDL) (2016)
Kleinberg, J.M.: Authoritative sources in a hyperlinked environment. J. ACM 46(5), 604–632 (1999)
Kunegis, J.: KONECT datasets: Koblenz network collection (2015). http://konect.uni-koblenz.de
Lempel, R., Moran, S.: SALSA: the stochastic approach for link-structure analysis. ACM Trans. Inf. Syst. (TOIS) 19(2), 131–160 (2001)
Liben-Nowell, D., Kleinberg, J.: The link-prediction problem for social networks. J. Am. Soc. Inf. Sci. Technol. 58(7), 1019–1031 (2007)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of the 27th Annual Conference on Neural Information Processing Systems 2013, pp. 3111–3119 (2013)
Mousazadeh, S., Cohen, I.: Embedding and function extension on directed graph. Sig. Process. 111(C), 137–149 (2015)
Ou, M., Cui, P., Pei, J., Zhang, Z., Zhu, W.: Asymmetric transitivity preserving graph embedding. In: KDD, pp. 1105–1114 (2016)
Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., Zhang, C.: Adversarially regularized graph autoencoder for graph embedding. In: IJCAI 2018, pp. 2609–2615 (2018)
Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: Proceedings of SIGKDD, pp. 701–710 (2014)
Perrault-Joncas, D.C., Meila, M.: Directed graph embedding: an algorithm based on continuous limits of Laplacian-type operators. In: Advances in Neural Information Processing Systems, pp. 990–998 (2011)
Recht, B., Re, C., Wright, S., Niu, F.: Hogwild: a lock-free approach to parallelizing stochastic gradient descent. In: Advances in Neural Information Processing Systems 24, pp. 693–701 (2011)
Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: Line: large-scale information network embedding. In: Proceedings of the 24th International Conference on World Wide Web, pp. 1067–1077 (2015)
Tsitsulin, A., Mottin, D., Karras, P., Müller, E.: Verse: versatile graph embeddings from similarity measures. In: Proceedings of the 2018 World Wide Web Conference, pp. 539–548 (2018)
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)
Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W.L., Leskovec, J.: Graph convolutional neural networks for web-scale recommender systems. In: KDD, pp. 974–983 (2018)
Zhou, C., Liu, Y., Liu, X., Liu, Z., Gao, J.: Scalable graph embedding for asymmetric proximity. In: AAAI Conference on Artificial Intelligence (AAAI 2017) (2017)
Acknowledgements
This work is partially funded by SoBigData (EU’s Horizon 2020 grant agreement No. 654024).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Khosla, M., Leonhardt, J., Nejdl, W., Anand, A. (2020). Node Representation Learning for Directed Graphs. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2019. Lecture Notes in Computer Science(), vol 11906. Springer, Cham. https://doi.org/10.1007/978-3-030-46150-8_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-46150-8_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-46149-2
Online ISBN: 978-3-030-46150-8
eBook Packages: Computer ScienceComputer Science (R0)
