Phase Transitions in Relational Learning
Machine Learning
Learning Logical Definitions from Relations
Machine Learning
| Hi-index | 0.01 |
A key step of supervised learning is testing whether a candidate hypothesis covers a given example. When learning in first order logic languages, the covering test is equivalent to a Constraint Satisfaction Problem (CSP). For critical values of some order parameters, CSPs present a phase pransition, that is, the probability of finding a solution abruptly drops from almost 1 to almost 0, and the complexity dramatically increases. This paper analyzes the complexity and feasibility of learning in first order logic languages with respect to the phase transition of the covering test.