A Study of Boolean Matrix Factorization Under Supervised Settings

Tatiana Makhalova (1, 2) , Martin Trnecka (3)

1 CS-HSE - Faculty of Computer Science [Moscow]
2 ORPAILLEUR - Knowledge representation, reasonning
3 Palacky University Olomouc

Boolean matrix factorization is a generally accepted approach used in data analysis to explain data. It is commonly used under unsu-pervised setting or for data preprocessing under supervised settings. In this paper we study factors under supervised settings. We provide an experimental proof that factors are able to explain not only data as a whole but also classes in the data.

Domaines: Informatique [cs]; Intelligence artificielle [cs.AI]

Tatiana Makhalova, Martin Trnecka. A Study of Boolean Matrix Factorization Under Supervised Settings. ICFCA 2019 - 15th International Conference on Formal Concept Analysis, Jun 2019, Frankfurt, Germany. pp.341-348, ⟨10.1007/978-3-030-21462-3_24⟩. ⟨hal-02162929v2⟩