Global multi-output decision trees for interaction prediction
Interaction data are characterized by two sets of objects, each described by their own set of features. They are often modeled as networks and the values of interest are the possible interactions between two instances, represented usually as a matrix. Here, a novel global decision tree learning method is proposed, where multi-output decision trees are constructed over the global interaction setting, addressing the problem of interaction prediction as a multi-label classification task. More specifically, the tree is constructed by splitting the interaction matrix both row-wise and column-wise, incorporating this way both interaction dataset features in the learning procedure. Experiments are conducted across several heterogeneous interaction datasets from the biomedical domain. The experimental results indicate the superiority of the proposed method against other decision tree approaches in terms of predictive accuracy, model size and computational efficiency. The performance is boosted by fully exploiting the multi-output structure of the model. We conclude that the proposed method should be considered in interaction prediction tasks, especially where interpretable models are desired.
KeywordsDecision tree Interaction data Heterogeneous networks Multi-output learning
- Blockeel, H., Raedt, L. D., & Ramon, J.: Top-down induction of clustering trees. In Proceedings of the 15th international conference on machine learning (ICML) (pp. 55–63). Morgan Kaufmann Publishers Inc., San Francisco (1998)Google Scholar
- Davis, J. & Goadrich, M.: The relationship between precision-recall and ROC curves. In Proceedings of the 23rd international conference on machine learning (ICML) (pp. 233–240). New York, USA (2006)Google Scholar
- Joly, A., Geurts, P., & Wehenkel, L.: Random forests with random projections of the output space for high dimensional multi-label classification. In Proceedings of the European conference on machine learning and knowledge discovery in databases, (ECML PKDD) (Vol. 8724, pp. 607–622) (2014)Google Scholar
- Mayer-Schönberger, V., & Cukier, K. (2014). Big data: A revolution that will transform how we live, work, and think. Boston: Houghton Mifflin Harcourt.Google Scholar
- Papagiannopoulou, C., Tsoumakas, G., & Tsamardinos, I.: Discovering and exploiting deterministic label relationships in multi-label learning. In Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, (KDD) (pp. 915–924) (2015)Google Scholar
- Pratanwanich, N., Lio, P., & Stegle, O.: Warped matrix factorisation for multi-view data integration. In Joint European conference on machine learning and knowledge discovery in databases (pp. 789–804). Springer (2016)Google Scholar
- Qi, G. J., Hua, X. S., Rui, Y., Tang, J., Mei, T., & Zhang, H. J.: Correlative multi-label video annotation. In Proceedings of the 15th ACM international conference on Multimedia (pp. 17–26). New York, USA (2007)Google Scholar
- Stock, M., Pahikkala, T., Airola, A., De Baets, B., & Waegeman, W. (2016). Efficient pairwise learning using kernel ridge regression: An exact two-step method. arXiv preprint arXiv:1606.04275.
- Tang, L., Rajan, S., & Narayanan, V.K.: Large scale multi-label classification via metalabeler. In Proceedings of the 18th international conference on World wide web (WWW) (pp. 211–220). New York, USA (2009)Google Scholar
- Tsoumakas, G., Katakis, I., & Vlahavas, I. (2009). Mining multi-label data. In O. Maimon & L. Rokach (Eds.), Data mining and knowledge discovery handbook. Boston: Springer.Google Scholar
- Vert, J. P. (2010). Reconstruction of biological networks by supervised machine learning approaches. In H. M. Lodhi & S. H. Muggleton (Eds.), Elements of computational systems biology (pp. 165–188). New York: Wiley.Google Scholar
- Witten, I. H., Frank, E., & Hall, M. A. (2016). Data mining: Practical machine learning tools and techniques (4th ed.). Burlington: Morgan Kaufmann.Google Scholar