Exact and approximate Boolean matrix decomposition with column-use condition

9Citations
Citations of this article
10Readers
Mendeley users who have this article in their library.

Abstract

An arbitrary m× n Boolean matrix M can be decomposed exactly as M= U∘ V, where U (resp. V) is an m× k (resp. k× n) Boolean matrix and ∘ denotes the Boolean matrix multiplication operator. The minimum k is called the Boolean rank of M, and it is known to be NP-hard to find it. With the interpretability issue in data mining applications in mind, we impose the column-use condition that the columns of U form a subset of the columns of the given M, and employ commonly used heuristics to find as small a k as possible.To this end, we first derive an exact closed-form formula, J= M¯ T∘ M¯ , such that M= M∘ JT holds, where J is maximal in the sense that if any 0 element in J is changed to a 1; then, this equality no longer holds. We measure the performance (in minimizing k) of our algorithms on several real benchmark datasets. The results demonstrate that one of our proposed algorithms performs as well or better on all but one of them than other representative heuristic algorithms, which do not impose the column-use condition and thus theoretically should find a smaller k.Boolean matrix decomposition with the column-use condition has wide applications. In educational databases, for example, the “ideal item response matrix” R, the “knowledge state matrix” A, and the “Q-matrix” Q play important roles. As they are related exactly by R¯ = A¯ ∘ QT, given R, we can find A and Q with a small number (k) of interpretable “knowledge states,” using our heuristics.

References Powered by Scopus

Learning the parts of objects by non-negative matrix factorization

11164Citations
N/AReaders
Get full text

A Threshold of ln n for Approximating Set Cover

2331Citations
N/AReaders
Get full text

Algorithms and applications for approximate nonnegative matrix factorization

1199Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Label Selection Algorithm Based on Boolean Interpolative Decomposition with Sequential Backward Selection for Multi-label Classification

4Citations
N/AReaders
Get full text

Label Selection Algorithm Based on Iteration Column Subset Selection for Multi-label Classification

3Citations
N/AReaders
Get full text

Rating Prediction Method for Item-Based Collaborative Filtering Recommender Systems Using Formal Concept Analysis

3Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Sun, Y., Ye, S., Sun, Y., & Kameda, T. (2016). Exact and approximate Boolean matrix decomposition with column-use condition. International Journal of Data Science and Analytics, 1(3–4), 199–214. https://doi.org/10.1007/s41060-016-0012-3

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 7

88%

Lecturer / Post doc 1

13%

Readers' Discipline

Tooltip

Computer Science 6

75%

Social Sciences 1

13%

Engineering 1

13%

Save time finding and organizing research with Mendeley

Sign up for free