Abstract
In the recent literature on multi-label classification, a lot of attention is given to methods that exploit label dependencies. Most of these methods assume that the dependencies are static over the entire instance space. In contrast, here we present an approach that dynamically adapts the label partitions in a multi-label decision tree learning context. In particular, we adapt the recently introduced predictive bi-clustering tree (PBCT) method towards multi-label classification tasks. This way, tree nodes can split the instance-label matrix both in a horizontal and a vertical way. We focus on hierarchical multi-label classification (HMC) tasks, and map the label hierarchy to a feature set over the label space. This feature set is exploited to infer vertical splits, which are regulated by a lookahead strategy in the tree building procedure. We evaluate our proposed method using benchmark datasets. Experiments demonstrate that our proposal (PBCT-HMC) obtained better or competitive results in comparison to its direct competitors, both in terms of predictive performance and model size. Compared to an HMC method that does not produce label partitions though, our method results in larger models on average, while still producing equally large or smaller models in one third of the datasets by creating suitable label partitions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
In our implementation, we consider a greedy generation of the subsets.
- 3.
Available at https://dtai.cs.kuleuven.be/clus/hmc-ens/.
- 4.
Available at https://dtai.cs.kuleuven.be/clus/hmcdatasets/.
- 5.
Available at https://itec.kuleuven-kulak.be/supportingmaterial.
- 6.
Available at http://kt.ijs.si/DragiKocev/PhD/resources/doku.php.
- 7.
Available at https://dtai.cs.kuleuven.be/clus.
- 8.
Available at https://github.com/biomal/Clus-PBCT-HMC.
References
Tsoumakas, G., Katakis, I.: Multi-label classification: an overview. Int. J. Data Warehouse. Min. (IJDWM) 3(3), 1–13 (2007)
Blockeel, H., Raedt, L.D., Ramon, J.: Top-down induction of clustering trees. In: Proceedings of the Fifteenth International Conference on Machine Learning, ICML 1998, pp. 55–63 (1998)
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, pp. 915–924. Association for Computing Machinery (2015)
Madjarov, G., Gjorgjevikj, D., Dimitrovski, I., Džeroski, S.: The use of data-derived label hierarchies in multi-label classification. J. Intell. Inf. Syst. 47(1), 57–90 (2016)
Szymanski, P., Kajdanowicz, T., Kersting, K.: How is a data-driven approach better than random choice in label space division for multi-label classification? CoRR (2016)
Joly, A., Geurts, P., Wehenkel, L.: Random forests with random projections of the output space for high dimensional multi-label classification. In: Machine Learning and Knowledge Discovery in Databases, pp. 607–622 (2014)
Breskvar, M., Kocev, D., Džeroski, S.: Multi-label classification using random label subset selections. In: Discovery Science (2017)
Breskvar, M., Kocev, D., Džeroski, S.: Ensembles for multi-target regression with random output selections. Mach. Learn. 107(11), 1673–1709 (2018). https://doi.org/10.1007/s10994-018-5744-y
Prati, R.C., de França, F.O.: Extending features for multilabel classification with swarm biclustering. In: IEEE Congress on Evolutionary Computation, pp. 2964–2971 (2013)
de Abreu, I.B.M., Mantovani, R.G., Cerri, R.: Incorporating instance correlations in multi-label classification via label-space. In: International Joint Conference on Neural Networks (IJCNN), pp. 581–588 (2017)
Feng, L., An, B., He, S.: Collaboration based multi-label learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3550–3557 (2019)
Pliakos, K., Geurts, P., Vens, C.: Global multi-output decision trees forinteraction prediction. Mach. Learn. 107(8), 1257–1281 (2018). https://doi.org/10.1007/s10994-018-5700-x
Elomaa, T., Malinen, T.: On lookahead heuristics in decision tree learning. In: Zhong, N., Raś, Z.W., Tsumoto, S., Suzuki, E. (eds.) ISMIS 2003. LNCS (LNAI), vol. 2871, pp. 445–453. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-39592-8_63
Vens, C., Struyf, J., Schietgat, L., Džeroski, S., Blockeel, H.: Decision trees for hierarchical multi-label classification. Mach. Learn. 73(2), 185 (2008)
Pliakos, K., Vens, C., Tsoumakas, G.: Predicting drug-target interactions with multi-label classification and label partitioning. In: IEEE-ACM Transactions On Computational Biology And Bioinformatics, pp. 1–11 (2019)
Schietgat, L., Vens, C., Struyf, J., Blockeel, H., Kocev, D., Dzeroski, S.: Predicting gene function using hierarchical multi-label decision tree ensembles. BMC Bioinf. 11, 2 (2010)
Cerri, R., Barros, R.C., de Carvalho, A.C., Jin, Y.: Reduction strategies for hierarchical multi-label classification in protein function prediction. BMC Bioinform. 17(1), 373 (2016) https://doi.org/10.1186/s12859-016-1232-1
Wehrmann, J., Cerri, R., Barros, R.: Hierarchical multi-label classification networks. In: Proceedings of the 35th International Conference on Machine Learning, vol. 80, pp. 5075–5084 (2018)
Masera, L., Blanzieri, E.: Awx: an integrated approach to hierarchical-multilabel classification. In: Machine Learning and Knowledge Discovery in Databases, pp. 322–336 (2019)
Tsoumakas, G., Katakis, I., Vlahavas, I.: Random k-labelsets for multi-label classification. IEEE Trans. Knowl. Data Eng. 23 1079–1089 (2011)
Moyano, J., Gibaja, E., Cios, K., Ventura, S.: Combining multi-labelclassifiers based on projections of the output space using evolutionary algorithms. Knowl.-Based Syst. 196, 105770 (2020)
Ruepp, A, Zollner, A.M.D.: The funcat, a functional annotation scheme for systematic classification of proteins from whole genomes. Nucleic Acids Res. 32(18), 5539–5545 (2004)
Nakano, F.K., Lietaert, M., Vens, C.: Machine learning for discovering missing or wrong protein function annotations. BMC Bioinf. 20(1), 485 (2019)
Dimitrovski. I., Kocev, D., Loskovska, S., Džeroski, S.: Hierchical annotation of medical images. In: Proceedings of the 11th International Multiconference - Information Society IS 200. IJS, Ljubljana, pp. 174–181 (2008)
Dimitrovski, I., Kocev, D., Loskovska, S., Džeroski, S.: Hierarchical classification of diatom images using ensembles of predictive clustering trees. Ecol. Inf. 7(1), 19–29 (2012)
Klimt, B., Yang, Y.: The Enron corpus: a new dataset for email classification research. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol. 3201, pp. 217–226. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-30115-8_22
Demšar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1–30 (2006)
Acknowledgments
We acknowledge Sao Paulo Research Foundation (FAPESP grants #2017/13218-5 and #2016/25078-0) and Research Fund Flanders (FWO) for financial support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Santos, B.Z., Nakano, F.K., Cerri, R., Vens, C. (2021). Predictive Bi-clustering Trees for Hierarchical Multi-label Classification. In: Hutter, F., Kersting, K., Lijffijt, J., Valera, I. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2020. Lecture Notes in Computer Science(), vol 12459. Springer, Cham. https://doi.org/10.1007/978-3-030-67664-3_42
Download citation
DOI: https://doi.org/10.1007/978-3-030-67664-3_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-67663-6
Online ISBN: 978-3-030-67664-3
eBook Packages: Computer ScienceComputer Science (R0)