Communications of the ACM
The Strength of Weak Learnability
Machine Learning
Prediction-preserving reducibility
Journal of Computer and System Sciences - 3rd Annual Conference on Structure in Complexity Theory, June 14–17, 1988
PAC-learnability of determinate logic programs
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Cryptographic limitations on learning Boolean formulae and finite automata
Journal of the ACM (JACM)
Inductive logic programming and learnability
ACM SIGART Bulletin
First-order jk-clausal theories are PAC-learnable
Artificial Intelligence
Identifying the Minimal Transversals of a Hypergraph and Related Problems
SIAM Journal on Computing
Pac-learning non-recursive Prolog clauses
Artificial Intelligence
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Learning first order universal Horn expressions
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Learning horn definitions: theory and an application to planning
New Generation Computing - Special issue on inductive logic programming 97
On the Desirability of Acyclic Database Schemes
Journal of the ACM (JACM)
Degrees of acyclicity for hypergraphs and relational database schemes
Journal of the ACM (JACM)
Conjunctive query containment revisited
Theoretical Computer Science - Special issue on the 6th International Conference on Database Theory—ICDT '97
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
Learning Logical Definitions from Relations
Machine Learning
Some Lower Bounds for the Computational Complexity of Inductive Logic Programming
ECML '93 Proceedings of the European Conference on Machine Learning
Learnability of Constrained Logic Programs
ECML '93 Proceedings of the European Conference on Machine Learning
Learning Range Restricted Horn Expressions
EuroCOLT '99 Proceedings of the 4th European Conference on Computational Learning Theory
Learning Acyclic First-Order Horn Sentences from Entailment
ALT '97 Proceedings of the 8th International Conference on Algorithmic Learning Theory
ALT '99 Proceedings of the 10th International Conference on Algorithmic Learning Theory
Learning First-Order Acyclic Horn Programs from Entailment
ILP '98 Proceedings of the 8th International Workshop on Inductive Logic Programming
The Complexity of Acyclic Conjunctive Queries
FOCS '98 Proceedings of the 39th Annual Symposium on Foundations of Computer Science
The complexity of unification.
The complexity of unification.
Algorithms for acyclic database schemes
VLDB '81 Proceedings of the seventh international conference on Very Large Data Bases - Volume 7
Pac-learning recursive logic programs: efficient algorithms
Journal of Artificial Intelligence Research
Pac-learning recursive logic programs: negative results
Journal of Artificial Intelligence Research
DS '01 Proceedings of the 4th International Conference on Discovery Science
On finding acyclic subhypergraphs
FCT'05 Proceedings of the 15th international conference on Fundamentals of Computation Theory
Proceedings of the 15th International Conference on Database Theory
ACM Transactions on Database Systems (TODS) - Invited papers issue
Hi-index | 0.00 |
A conjunctive query problem in relational database theory is a problem to determine whether or not a tuple belongs to the answer of a conjunctive query over a database. Here, a tuple and a conjunctive query are regarded as a ground atom and a nonrecursive function-free definite clause, respectively. While the conjunctive query problem is NP-complete in general, it becomes efficiently solvable if a conjunctive query is acyclic. Concerned with this problem, we investigate the learnability of acyclic conjunctive queries from an instance with a j-database which is a finite set of ground unit clauses containing at most j-ary predicate symbols. We deal with two kinds of instances, a simple instance as a set of ground atoms and an extended instance as a set of pairs of a ground atom and a description. Then, we show that, for each j ≥ 3, there exist a j-database such that acyclic conjunctive queries are not polynomially predictable from an extended instance under the cryptographic assumptions. Also we show that, for each n 0 and a polynomial p, there exists a p(n)- database of size O(2p(n)) such that predicting Boolean formulae of size p(n) over n variables reduces to predicting acyclic conjunctive queries from a simple instance. This result implies that, if we can ignore the size of a database, then acyclic conjunctive queries are not polynomially predictable from a simple instance under the cryptographic assumptions. Finally, we show that, if either j = 1, or j = 2 and the number of element of a database is at most l (≥ 0), then acyclic conjunctive queries are paclearnable from a simple instance with j-databases.