Synthetic dataset generator for multi-label classification with control of label correlation

• Maria Luiza S. de Sousa Universidade de São Paulo (USP) https://orcid.org/0009-0009-2070-1043
• Marcelo de Souza Lauretto Universidade de São Paulo (USP) https://orcid.org/0000-0001-5507-2368
• Helena Brentani Universidade de São Paulo (USP) https://orcid.org/0000-0001-5192-4682
• Fátima L. S. Nunes Universidade de São Paulo (USP) http://orcid.org/0000-0003-0040-0752
• Ariane Machado-Lima Universidade de São Paulo (USP) https://orcid.org/0000-0002-5719-338X

DOI: https://doi.org/10.5753/bresci.2026.249395

Resumo

In Data Science, synthetic datasets allow comparing algorithms under controlled conditions. In multi-label classification, current dataset generators ignore label associations, which is relevant in areas such as medicine to represent comorbidities, for instance. This work proposes a generator that explicitly incorporates these associations. Each instance is created by two mechanisms: (i) label generation using conditional co-occurrence probabilities; (ii) feature generation with normal distributions whose mean depends on the present labels. Its differential is enabling algorithm analysis and comparison while simultaneously controlling label correlation and their separability in the feature space.

Palavras-chave: Synthetic data generation, Multi-label classification, Label correlation, Conditional label dependencies, Feature generation

Referências

Charte, F., Rivera, A. J., del Jesus, M. J., and Herrera, F. (2015). MLSMOTE: Approaching imbalanced multilabel learning through synthetic instance generation. Knowledge-Based Systems, 89:385–397.

Madjarov, G., Kocev, D., Gjorgjevikj, D., and Džeroski, S. (2012). An extensive experimental comparison of methods for multi-label learning. Pattern Recognition, 45(9):3084–3104.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in python. Journal of Machine Learning Research, 12:2825–2830.

Tomás, J. T., Spolaôr, N., Cherman, E. A., and Monard, M. C. (2014). A framework to generate synthetic multi-label datasets. Electronic Notes in Theoretical Computer Science, 302:155–176.

Tsoumakas, G. and Katakis, I. (2007). Multi-label classification: An overview. In International Journal of Data Warehousing and Mining.

Zhang, M.-L. and Zhou, Z.-H. (2014). A review on multi-label learning algorithms. IEEE Transactions on Knowledge and Data Engineering, 26(8):1819–1837.

Zhang, M.-L. and Zhou, Z.-H. (2020). Multi-label learning: From problem transformation to algorithm adaptation. IEEE Transactions on Knowledge and Data Engineering.