Monte Carlo Partitioning of Graphs with a Self-Organizing Map

A Monte Carlo algorithm for partitioning graphs is presented. The algorithm is based on the self-organizing map, an unsupervised, competitive neural network. A mean-field analysis suggests that the complexity of the algorithm is at most is on the order of O(n3/|E|), where n is the number of vertices of the graph, and |E| the number of edges. This prediction is tested on a class of random graphs. Scaling laws that deviate from the mean-field prediction are obtained. Although the origin of these scaling laws is unclear, their consequences are discussed.

[1]  Richard Durbin,et al.  An analogue approach to the travelling salesman problem using an elastic net method , 1987, Nature.

[2]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[3]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[4]  Thomas Martinetz,et al.  Topology representing networks , 1994, Neural Networks.

[5]  P. Anderson,et al.  Application of statistical mechanics to NP-complete problems in combinatorial optimisation , 1986 .

[6]  David S. Johnson,et al.  Some Simplified NP-Complete Graph Problems , 1976, Theor. Comput. Sci..

[7]  Bernard Angéniol,et al.  Self-organizing feature maps and the travelling salesman problem , 1988, Neural Networks.

[8]  Carsten Peterson,et al.  Neural Networks for Optimization Problems with Inequality Constraints: The Knapsack Problem , 1993, Neural Computation.

[9]  Carsten Peterson,et al.  Parallel Distributed Approaches to Combinatorial Optimization: Benchmark Studies on Traveling Salesman Problem , 1990, Neural Computation.

[10]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[11]  Brian W. Kernighan,et al.  An efficient heuristic procedure for partitioning graphs , 1970, Bell Syst. Tech. J..

[12]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[13]  Carsten Peterson,et al.  Complex Scheduling with Potts Neural Networks , 1992, Neural Computation.

[14]  Richard Durbin,et al.  A dimension reduction framework for understanding cortical maps , 1990, Nature.

[15]  Graeme Mitchison,et al.  A Type of Duality between Self-Organizing Maps and Minimal Wiring , 1995, Neural Computation.