Positive Unlabeled Link Prediction via Transfer Learning for Gene Network Reconstruction
- 1 Citations
- 625 Downloads
Abstract
Transfer learning can be employed to leverage knowledge from a source domain in order to better solve tasks in a target domain, where the available data is exiguous. While most of the previous papers work in the supervised setting, we study the more challenging case of positive-unlabeled transfer learning, where few positive labeled instances are available for both the source and the target domains. Specifically, we focus on the link prediction task on network data, where we consider known existing links as positive labeled data and all the possible remaining links as unlabeled data. In many real applications (e.g., in bioinformatics), this usually leads to few positive labeled data and a huge amount of unlabeled data. The transfer learning method proposed in this paper exploits the unlabeled data and the knowledge of a source network in order to improve the reconstruction of a target network. Experiments, conducted in the biological field, showed the effectiveness of the proposed approach with respect to the considered baselines, when exploiting the Mus Musculus gene network (source) to improve the reconstruction of the Homo Sapiens Sapiens gene network (target).
Notes
Acknowledgments
We would like to acknowledge the European project MAESTRA - Learning from Massive, Incompletely annotated, and Structured Data (ICT-2013-612944).
References
- 1.Platt, J.C.: Probabilistic outputs for support vector machine and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers (1999)Google Scholar
- 2.Ceci, M., Pio, G., Kuzmanovski, V., Džeroski, S.: Semi-supervised multi-view learning for gene network reconstruction. Plos One, 10(12), e0144031 (2015)CrossRefGoogle Scholar
- 3.Dai, W., Yang, Q., Xue, G., Yu, Y.: Boosting for transfer learning. In: Proceedings of ICML, pp. 193–200 (2007)Google Scholar
- 4.Elkan, C., Noto, K.: Learning classifiers from only positive and unlabeled data. In: Proceedings of ACM SIGKDD, pp. 213–220 (2008)Google Scholar
- 5.Jowkar, G., Mansoori, E.: Perceptron ensemble of graph-based positive unlabeled learning for disease gene identification. Comput. Biol. Chem. 64, 263–270 (2016)MathSciNetCrossRefGoogle Scholar
- 6.Levatic, J., Ceci, M., Kocev, D., Dzeroski, S.: Self-training for multi-target regression with tree ensembles. Knowl. Based Syst. 123, 41–60 (2017)CrossRefGoogle Scholar
- 7.Levatic, J., Kocev, D., Ceci, M., Dzeroski, S.: Semi-supervised trees for multi-target regression. Inf. Sci. 450, 109–127 (2018)MathSciNetCrossRefGoogle Scholar
- 8.Liu, B., Lee, W.S., Yu, P.S., Li, X.: Partially supervised classification of text documents. In: Proceedings of ICML, pp. 387–394 (2002)Google Scholar
- 9.Marbach, D., et al.: Wisdom of crowds for robust gene network inference. Nat. Meth. 9(8), 796–804 (2016)CrossRefGoogle Scholar
- 10.Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
- 11.Pan, S.J., Zheng, V.W., Yang, Q., Hu, D.H.: Transfer learning for wifi-based indoor localization. In: Workshop on Transfer Learning for Complex Task AAAI (2008)Google Scholar
- 12.Pio, G., Ceci, M., Malerba, D., D’Elia, D.: ComiRNet:a web-based system for the analysis of miRNA-gene regulatory networks. BMC Bioinform. 16(S-9), S7 (2015)CrossRefGoogle Scholar
- 13.Pio, G., Malerba, D., D’Elia, D., Ceci, M.: Integrating microRNA target predictions for the discovery of gene regulatory networks: a semi-supervised ensemble learning approach. BMC Bioinform. 15(S-1), S4 (2014)CrossRefGoogle Scholar
- 14.Weiss, K.R., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. J. Big Data 3, 9 (2016)CrossRefGoogle Scholar
- 15.Yang, X., Song, Q., Wand, Y.: A weighted support vector machine for data classification. Int. J. Pattern Recogn. 21, 961–976 (2007)CrossRefGoogle Scholar
- 16.Zhang, B., Zuo, W.: Learning from positive and unlabeled examples: a survey. In: ISIP/WMWA, pp. 650–654 (2008)Google Scholar