Recurrent neural network approach for partitioning irregular graphs
This paper is concerned with utilizing a neural network approach to solve the k-way partitioning problem. The k-way partitioning is modeled as a constraint satisfaction problem with linear inequalities and binary variables. A new recurrent neural network architecture is proposed for k-way partitioning. This network is based on an energy function that controls the competition between the partition's external cost and the penalty function. This method is implemented and compared to other global search techniques such as simulated annealing and genetic algorithms. It is shown that it converges better than these techniques.
KeywordsGenetic Algorithm Cost Function Simulated Annealing Internal Energy Penalty Function
Unable to display preview. Download preview PDF.
- 1.S.T. Barnard and H.D. Simon. A Fast Multilevel Implementation of Recursive Spectral Bisection for Partitioning Unstructured Problems. In Proceedings of the 6th SIAM Conference on Parallel Processing for Scientific Computing, pages 711–718, 1993.Google Scholar
- 4.C.C. Gonzaga. Path-following methods for linear programming. SIAM Review, 32(2):167–224.Google Scholar
- 5.B. Hendrickson and R. Leland. An Improved Spectral Graph partitioning Algorithm for mapping parallel Computations. Technical Report SAND92-1460, Sandia National labs, Albuquerque, NM, 1992.Google Scholar
- 6.B. Hendrickson and R. Leland. A Multilevel Algorithm for Partitioning Graphs. Technical Report SAND93-1301, Sandia National labs, Albuquerque, NM., 1993.Google Scholar
- 7.J.J. Hpfield and D.W. Tank. Neural computation of decisions in optimization problems. Biological Cybernitics, 52:141–152, 1985.Google Scholar
- 10.G. Karypis and V. Kumar. A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs. Technical Report TR95-035, Department of Computer Science, University of Minnesota, July 1995.Google Scholar
- 11.G. Karypis and V. Kumar. Parallel Multilevel Graph Partitioning. Technical Report TR 95-036, Department of Computer Science, University of Minnesota, June 1995.Google Scholar
- 12.M-Tahar Kechadi and D.F. Hegarty. A parallel technique for graph partitioning problems. In Proceedings of The International Conference and Exhibition on High-Performance Computing and Networking (HPCN), pages 449–457, Amsterdam, Netherlands, April 20–23 1998, Springer.Google Scholar
- 13.B. Kernighan and S. Lin. An Efficient Heuristic Procedure for Partitioning Graphs. Bell Syst. Tech. Journal, 29:291–307, February 1970.Google Scholar
- 14.G.L. Miller, S-H. Teng, and S.A. Vavasis. A Unified Geometric Approach to Graph Separators. In Proceedings of the 31st Annual Symposium on Foundations of Computer Science, pages 538–547, 1991.Google Scholar
- 16.A. Pothen, H.D. Simon, L. Wang, and S.T. Barnard. Towards a Fast Implementation of Spectral Nested Disection. In Proceedings of Supercomputing'92, pages 42–51, 1992.Google Scholar