Information Processing Letters
The hardest constraint problems: a double phase transition
Artificial Intelligence
An introduction to computational learning theory
An introduction to computational learning theory
Pruning Algorithms for Rule Learning
Machine Learning
Constructing an asymptotic phase transition in random binary constraint satisfaction problems
Theoretical Computer Science - Phase transitions in combinatorial problems
Phase Transitions in Relational Learning
Machine Learning
Learning Conjunctive Concepts in Structural Domains
Machine Learning
On the Complexity of Some Inductive Logic Programming Problems
ILP '97 Proceedings of the 7th International Workshop on Inductive Logic Programming
Relational learning as search in a critical region
The Journal of Machine Learning Research
Random constraint satisfaction: Easy generation of hard (satisfiable) instances
Artificial Intelligence
Extension of the Top-Down Data-Driven Strategy to ILP
Inductive Logic Programming
Exact phase transitions in random constraint satisfaction problems
Journal of Artificial Intelligence Research
An experimental study of phase transitions in matching
IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
Determinate literals in inductive logic programming
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
Learning on the phase transition edge
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 2
Empirical Study of Relational Learning Algorithms in the Phase Transition Framework
ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part I
Learning discriminant rules as a minimal saturation search
ILP'10 Proceedings of the 20th international conference on Inductive logic programming
Hi-index | 0.00 |
The feasibility of symbolic learning strongly relies on the efficiency of heuristic search in the hypothesis space. However, recent works in relational learning claimed that the phase transition phenomenon which may occur in the subsumption test during search acts as a plateau for the heuristic search, strongly hindering its efficiency. We further develop this point by proposing a learning problem generator where it is shown that top-down and bottom-up learning strategies face a plateau during search before reaching a solution. This property is ensured by the underlying CSP generator, the RB model, that we use to exhibit a phase transition of the subsumption test. In this model, the size of the current hypothesis maintained by the learner is an order parameter of the phase transition and, as it is also the control parameter of heuristic search, the learner has to face a plateau during the problem resolution. One advantage of this model is that small relational learning problems with interesting properties can be constructed and therefore can serve as a benchmark model for complete search algorithms used in learning. We use the generator to study complete informed and non-informed search algorithms for relational learning and compare their behaviour when facing a phase transition of the subsumption test. We show that this generator exhibits the pathological case where informed learners degenerate into non-informed ones.