Tree decomposition with applications to constraint processing

Authors:
Itay Meiri;Rina Dechter;Judea Pearl
Affiliations:
Cognitive Systems Laboratory, Computer Science Department, University of California, Los Angeles, CA;Computer Science Department, Technion - Israel, Institute of Technology, Haifa, Israel and Cognitive Systems Laboratory, Computer Science Department, University of California, Los Angeles, CA;Cognitive Systems Laboratory, Computer Science Department, University of California, Los Angeles, CA
Venue:
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 1
Year:
1990

Citing 6
Cited 1

The complexity of some polynomial network consistency algorithms for constraint satisfaction problems

Artificial Intelligence
Decomposing an N-ary relation into a tree of binary relations

PODS '87 Proceedings of the sixth ACM SIGACT-SIGMOD-SIGART symposium on Principles of database systems
Network-based heuristics for constraint-satisfaction problems

Artificial Intelligence
A Sufficient Condition for Backtrack-Free Search

Journal of the ACM (JACM)
Graph Algorithms

Graph Algorithms
Theory of Relational Databases

Theory of Relational Databases

Pairwise decomposition for combinatorial optimization in graphical models

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper concerns the task of removing redundant information from a given knowledge base, and restructuring it in the form of a tree, so as to admit efficient problem solving routines. We offer a novel approach which guarantees the removal of all redundancies that hide a tree structure. We develop a polynomial time algorithm that, given an arbitrary constraint network, generates a precise tree representation whenever such a tree can be extracted from the input network; otherwise, the fact that no tree representation exists is acknowledged, and the tree generated may serve as a good approximation to the original network.