Abstract
Link prediction is a fundamental task that predicts whether a link exists between two nodes based on the currently observed network. Existing approaches such as heuristic-based algorithms assume that two nodes are likely to have a link in a network. In fact, they limit algorithm effectiveness when the assumptions are not correct. Moreover, these link prediction algorithms lack generalization ability, which indicates that they have different effects on different types of networks. For example, the common neighbours algorithm works well on social networks, but it shows poor performance on electric power networks. Inspired by the image inpainting technology of generative adversarial networks and the adjacency matrix representation of networks, we propose a new framework for link prediction based on the image inpainting method, named the Generative Image Inpainting for Link Prediction algorithm (GIILP), to address these problems. The key idea of the GIILP is that the network can be converted into an image (the image is a form of the adjacency matrix (two dimensions)). Pixel values represent the likelihood of two nodes. Thus, the problem of predicting a possible link between nodes is converted into filling missing pixels in an image. The link information of the network can be expressed by the image information, which means that our algorithm does not need assumptions such as heuristics, and works regardless of the dataset type. The experimental results on multiple link prediction public datasets demonstrate that our algorithm has an advantage over other algorithms, including heuristic-based and deep learning methods.
Similar content being viewed by others
References
Liben-Nowell D, Kleinberg J (2003) The link-prediction problem for social networks. Wiley subscription services, vol 58. A Wiley Company Inc, pp 556–559
Adamic L, Aar EA (2003) Friends and neighbors on the web. Soc Netw, 211–230
Zhang M, Chen Y (2018) Link prediction based on graph neural networks. In: International conference on neural information processing systems, pp 5171–5181
Symeonidis P, Iakovidou N, Mantas N, Manolopoulos Y (2013) From biological to social networks: link prediction based on multi-way spectral clustering. Data Knowl Eng, 226–242
Lu L, Zhou T (2010) Link prediction in complex networks: a survey. Physica Stat Mech Appl 390(6):1150–1170
Paul J (1901) tude comparative de la distribution florale dans une portion des Alpes et des Jura. Bull Soc Vaudoise Sci Nat, 547–579
Kate L (1953) A new status index derived from sociometric analysis. Psychometrika, 39–43
Haveliwala T, Kamvar A, Jeh G (2003) An analytical comparison of approaches to personalizing pagerank. Stanford
Yang G, Yanping Z, Fulan Q, Shu Z (2017) Link prediction algorithm based on node similarity of triadic closure. J Front Comput Sci Technol, 822–832
Barabsi AL, Albert R (1999) Emergence of scaling in random networks. Science, 509–512
Zhou T, Lv L, Zhang YC (2009) Predicting missing links via local information. Europ Phys J B, 623–630
Jeh G, Widom J (2002) SimRank: a measure of structural-context similarity. In: Proceedings of the eighth ACM SIGKDD international conference on knowledge discovery and data mining, pp 538–543
Klein DJ, Randi M (1993) Resistance distance. J Math Chem, 81–95
Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. IEEE Comput 42(8):30–37
Nickel M, Murphy K, Tresp V, Gabrilovich E (2015) A review of relational machine learning for knowledge graphs. Proc IEEE 104(1):11–33
Airoldi EM, Blei DM, Fienberg SE, Xing EP (2008) Mixed membership stochastic blockmodels. J Mach Learn Res 9(5):1981
Kumar A, Singh S, Singh K, Biswas B (2019) Level-2 node clustering coefficient-based link prediction. Appl Intell 49:2762–2779
Duan L, Ma S, Aggarwal C, Ma T, Huai J (2017) An ensemble approach to link prediction. IEEE Trans Knowl Data Eng 29(11):2402–2416
Sze V, Chen Y, Yang TJ, Emer JS (2017) Efficient processing of deep neural networks: a tutorial and survey. Proc IEEE 105(12):2295–2329
Tang D, Qin B, Liu T (2015) Document modeling with gated recurrent neural network for sentiment classification. In: Conference on empirical methods in natural language processing, pp 1422–1432
Ballester C, Bertalmio M, Caselles V, Sapiro G (2001) Filling-in by joint interpolation of vector fields and gray levels. IEEE Trans Image Process Public IEEE Signal Process Soc 10(8):1200– 1211
Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. In: International conference on neural information processing systems, vol 60, pp 1097–1105
Jaderberg M, Simonyan K, Zisserman A, Kavukcuoglu K (2015) Spatial transformer networks. In: International conference on neural information processing systems, pp 2017–2025
Lommatzsch A (2009) Learning spectral graph transformations for link prediction. In: Proceedings of the 26th annual international conference on machine learning. ACM, pp 561–568
Jeon Y, Kim J (2017) Active convolution: learning the shape of convolution for image classification. In: IEEE Conference on computer vision and pattern recognition, pp 1846–1854
Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2009) The graph neural network model. IEEE Trans Neural Netw 20(1):61
Zhang M, Tang J, Qu M, Yan J, Wang M (2015) Line: large-scale information network embedding. In: Proceedings of the 24th international conference on World Wide Web, pp 1067–1077
Perozzi B, Alrfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 701–710
Grover A, Leskovec J (2016) node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 855–864
Mikolov T, Sutskever I, Chen K, Corrado G, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Proceedings of the 26th international conference on neural information processing systems, pp 3111–3119
Zhang M, Chen Y (2017) Weisfeiler-Lehman neural machine for link prediction. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 575–583
Yana k., Egor S, Akmal A (2019) Spring-electrical models for link prediction. In: Proceedings of the 12th ACM international conference on web search and data mining, pp 708–716
Yana k., Egor S, Akmal A (2019) Spring-electrical models for link prediction. In: Proceedings of the 12th ACM international conference on web search and data mining, pp 708–716
Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436
Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S (2014) Generative adversarial nets. In: International conference on neural information processing systems, vol 3, pp 2672–2680
Yu J, Lin Z, Yang J, Shen X, Lu X, Huang TS (2018) Generative image inpainting with contextual attention. In: IEEE Conference on computer vision and pattern recognition, pp 5505–5514
Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville A (2017) Improved training of wasserstein gans. In: International conference on neural information processing systems, pp 5767–5777
Arjovsky M, Chintala S, Bottou L (2017) Wasserstein gan. In: International conference on machine learning, pp 214–223
Gao M, Chen L, Li B, Liu W (2018) A link prediction algorithm based on low-rank matrix completion. Appl Intell 48:4531–4550
Qian F, Yang Q, Ma C, Zhang Y (2019) Link prediction algorithm of weighted friend recommendation model. Journal of Frontiers of Computer Science & Technology
Qian F, Gao Y, Zhao S, Tang J, Zhang Y (2017) Combining topological properties and strong ties for link prediction. Tsinghua Sci Technol, 595–608
Shervashidze N, Schweitzer P, Leeuwen EJV, Mehlhorn K, Borgwardt KM (2011) Weisfeiler-lehman graph kernels. J Mach Learn Res 12(3):2539–2561
Bo K, Jefrey L, Tijl D (2019) Conditional network embeddings. In: Proceedings of the international conference on learning representations
Acknowledgements
This work was jointly supported by the National Key Research and Development Program of China (2017YFB1401903), the Natural Science Foundation of China (No. 61673020, No. 61702003, No. 61876001), and the Natural Science Foundation of Anhui Province (1808085MF175). The authors would also like to thank the anonymous reviewers for their valuable comments.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Qian, F., Li, J., Du, X. et al. Generative image inpainting for link prediction. Appl Intell 50, 4482–4494 (2020). https://doi.org/10.1007/s10489-020-01648-w
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-020-01648-w