A novel neural network approach to solve exact and inexact graph isomorphism problems

Authors:
Brijnesh J. Jain;Fritz Wysotzki
Affiliations:
Dept. of Electrical Engineering and Computer Science, TU Berlin, Berlin, Germany;Dept. of Electrical Engineering and Computer Science, TU Berlin, Berlin, Germany
Venue:
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Year:
2003

Citing 6
Cited 1

Matching Hierarchical Structures Using Association Graphs

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Winner-Takes-All Networks for the Maximum Clique Problem

KI '02 Proceedings of the 25th Annual German Conference on AI: Advances in Artificial Intelligence
Replicator Equations, Maximal Cliques, and Graph Isomorphism

Neural Computation
A novel optimizing network architecture with applications

Neural Computation
A versatile computer-controlled assembly system

IJCAI'73 Proceedings of the 3rd international joint conference on Artificial intelligence
A Lagrangian relaxation network for graph matching

IEEE Transactions on Neural Networks

A competitive winner-takes-all architecture for classification and pattern recognition of structures

GbRPR'03 Proceedings of the 4th IAPR international conference on Graph based representations in pattern recognition

Quantified Score

Hi-index	0.01

Visualization

Abstract

We present a neural network approach to solve exact and inexact graph isomorphism problems for weighted graphs. In contrast to other neural heuristics or related methods our approach is based on approximating the automorphism partition of a graph to reduce the search space followed by an energy-minimizing matching process. Experiments on random graphs with 100-5000 vertices are presented and discussed.