TY - JOUR

T1 - Recovering noisy contexts with probabilistic formal concepts?

AU - Martynovich, Vitaliy V.

AU - Vityaev, Euvgeniy E.

PY - 2016

Y1 - 2016

N2 - The uncertainty in the environment typically generates noisy concept alternatives and leads to an overpopulated concept lattice. From a computational point of view, a straightforward filtering of the noisy concept lattice will suffer from an exponential-size computational overkill, and from a semantical one [ will face numerous ambiguities due to an overfitting. We managed to bypass the filtering problem by applying a sort of probabilistic approach. We developed a probabilistic generaliza-tion of formal concepts which seems to avoid a monstrous combinatorial complexity of a complete context lattice construction. The theoretical base for this method is described, as well as a ready-to-work noise resis-tant algorithm. The algorithm has been tested and showed a moderate precision and recall rate on various datasets, including a toy one pre-sented with the presence of a 2, 3 or 5% random noise.

AB - The uncertainty in the environment typically generates noisy concept alternatives and leads to an overpopulated concept lattice. From a computational point of view, a straightforward filtering of the noisy concept lattice will suffer from an exponential-size computational overkill, and from a semantical one [ will face numerous ambiguities due to an overfitting. We managed to bypass the filtering problem by applying a sort of probabilistic approach. We developed a probabilistic generaliza-tion of formal concepts which seems to avoid a monstrous combinatorial complexity of a complete context lattice construction. The theoretical base for this method is described, as well as a ready-to-work noise resis-tant algorithm. The algorithm has been tested and showed a moderate precision and recall rate on various datasets, including a toy one pre-sented with the presence of a 2, 3 or 5% random noise.

KW - Association rules

KW - Classification task

KW - Concept lattice

KW - Data mining

KW - Formal concept analysis

KW - Inductive learning

UR - http://www.scopus.com/inward/record.url?scp=84990833594&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84990833594

VL - 1687

SP - 24

EP - 35

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

T2 - 2nd International Workshop on Soft Computing Applications and Knowledge Discovery, SCAKD 2016

Y2 - 18 July 2016

ER -