On the usability of probably approximately correct implication bases

DOI10.1007/978-3-319-59271-8_5MaRDI QIDQ2399919zbMATH OpenOpenAlexWikidataFDO

Authors Daniel Borchmann, Tom Hanika, Sergei Obiedkov

Publication date 25 August 2017

Full work available at URL https://arxiv.org/abs/1701.00877

zbMATH Keywords

formal concept analysisquery learningPAC learningimplications

Mathematics Subject Classification ID

Knowledge representation (68T30)

Abstract: We revisit the notion of probably approximately correct implication bases from the literature and present a first formulation in the language of formal concept analysis, with the goal to investigate whether such bases represent a suitable substitute for exact implication bases in practical use-cases. To this end, we quantitatively examine the behavior of probably approximately correct implication bases on artificial and real-world data sets and compare their precision and recall with respect to their corresponding exact implication bases. Using a small example, we also provide qualitative insight that implications from probably approximately correct bases can still represent meaningful knowledge from a given data set.

Recommendations

• From equivalence queries to PAC learning: the case of implication theories
• Probabilistic generalization of formal concepts
• Implications over probabilistic attributes
• Probabilistic concepts in formal contexts
• Probabilistic formal concepts with negation

Cited in

(4)

• Approximate computation of exact association rules
• Formal Methods in FCA and Big Data
• scientific article; zbMATH DE number 991162 (Why is no real title available?)
• From equivalence queries to PAC learning: the case of implication theories

This page was built for publication: On the usability of probably approximately correct implication bases

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2399919)