K-way neural network graph partitioning with separator vertices

Abstract.A neural network for partitioning graphs into any number of subgraphs using a k-way procedure is presented. The resulting neural network optimises all subgraphs so that they contain approximately the same number of vertices with the exception of a `separator' subgraph. The latter separates all the other subgraphs and is optimised to contain a minimum number of vertices. Expressions for the neuron link weights for such a network are derived analytically, and the recall mechanism of the mean field theorem neural network is used to obtain the graph partitioning. Applications focus on partitioning graphs associated with finite element meshes which, together with parallel domain decomposition solution methods, provide the motivation for this work.

[1]  Alex Pothen,et al.  PARTITIONING SPARSE MATRICES WITH EIGENVECTORS OF GRAPHS* , 1990 .

[2]  William Gropp,et al.  A comparison of domain decomposition techniques for elliptic partial differential equations and their parallel implementation , 1985, PP.

[3]  Vipin Kumar,et al.  A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs , 1998, SIAM J. Sci. Comput..

[4]  David E. van den Bout,et al.  Graph partitioning using annealed neural networks , 1990, International 1989 Joint Conference on Neural Networks.

[5]  Ardeshir Bahreininejad,et al.  Finite element mesh partitioning using neural networks , 1996 .

[6]  Carsten Peterson,et al.  Neural Networks and NP-complete Optimization Problems; A Performance Study on the Graph Bisection Problem , 1988, Complex Syst..

[7]  Fernando J. Pineda,et al.  Generalization of Back propagation to Recurrent and Higher Order Neural Networks , 1987, NIPS.

[8]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[9]  C. Hirsch,et al.  Numerical Computation of Internal and External Flows. By C. HIRSCH. Wiley. Vol. 1, Fundamentals of Numerical Discretization. 1988. 515 pp. £60. Vol. 2, Computational Methods for Inviscid and Viscous Flows. 1990, 691 pp. £65. , 1991, Journal of Fluid Mechanics.

[10]  Vipin Kumar,et al.  A parallel formulation of interior point algorithms , 1994, Proceedings of Supercomputing '94.

[11]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.