Relation decomposition: the theory

Authors:
Robert Martin Haralick;Ligon Liu;Evan Misshula
Affiliations:
Computer Science, Graduate Center, City University of New York, New York, NY;Computer Science, Graduate Center, City University of New York, New York, NY;Computer Science, Graduate Center, City University of New York, New York, NY
Venue:
MLDM'13 Proceedings of the 9th international conference on Machine Learning and Data Mining in Pattern Recognition
Year:
2013

Citing 2
Cited 0

Axioms of causal relevance

Artificial Intelligence - Special issue on relevance
Multivalued dependencies and a new normal form for relational databases

ACM Transactions on Database Systems (TODS)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Data Mining explanatory models must deal with relevance: how values of different data items are relevant to the values of other data items. But to be able to construct explanatory models, and in particular causal explanatory models, we must do so by first understanding irrelevance and exactly how irrelevance plays a role in explanatory models. The reason is that the conditional irrelevance or conditional no influence relation defines the boundaries of the ballpark within which an explanatory model lives. This paper reviews the theory of no influence in the mathematical relation data structure. We discuss the relationship this theory has to graphical models and we define a coefficient of no influence and give a method for the estimation of its p-value.