Self-Organizing Graphs — A Neural Network Perspective of Graph Layout
The paper presents self-organizing graphs, a novel approach to graph layout based on a competitive learning algorithm. This method is an extension of self-organization strategies known from unsupervised neural networks, namely from Kohonen’s self-organizing map. Its main advantage is that it is very flexibly adaptable to arbitrary types of visualization spaces, for it is explicitly parameterized by a metric model of the layout space. Yet the method consumes comparatively little computational resources and does not need any heavy-duty preprocessing. Unlike with other stochastic layout algorithms, not even the costly repeated evaluation of an objective function is required. To our knowledge this is the first connectionist approach to graph layout. The paper presents applications to 2D-layout as well as to 3D-layout and to layout in arbitrary metric spaces, such as networks on spherical surfaces.
KeywordsCompetitive Learning Graph Layout Layout Area Kohonen Network Competitive Layer
- J.A. Anderson and E. Rosenfeld, editors. Neurocomputing. MIT Press, Combridge /MA, 1988.Google Scholar
- F.J. Brandenburg, editor. Graph Drawing GD’95. Springer, Passau, Germany, September 1995.Google Scholar
- F.J. Brandenburg, M. Himsolt, and C. Rohrer. An experimental comparison of force-directed and randomized graph drawing algorithms. In , pages 76–87.Google Scholar
- I.F. Cruz and J.P. Twarog. 3D graph drawing with simulated annealing. In , pages 162–165.Google Scholar
- R. Davidson and D. Harel.Drawing graphs nicely using simulated annealing. ACM Transactions on Graphics, 15(4):301–331, October 1996.Google Scholar
- P. Frasconi, M. Gori, and A. Sperduti. A general framework for adaptive processing of data structures. Technical Report 15/97, Universita di Firenze, Florence, 1997.Google Scholar
- B. Fritzke. Some competitive learning methods. Unpublished manuscript. http://www.neuroinformatik.ruhr-uni-bochum.de/ini/VDM/research/gsn/JavaPaper/, April 1997.
- C. Goller and A. Küchler. Learning task-dependent distributed representations by backpropagation through structure. In International Conference on Neural Networks (ICNN-96), 1996.Google Scholar
- J. Hertz, A. Krogh, and R.G. Palmer. Introduction to the Theory of Neural Computation. Addison-Wesley, Redwood City/CA, 1991.Google Scholar
- D. Hubel and T. Wiesel. Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. Journal of Physiology, 160:173–181, 1962.Google Scholar
- T. Kohonen. Self-Organization and Associative Memory. Springer, New York, 1989.Google Scholar
- T. Kohonen.Self-Organizing Maps. Springer, New York, 1997.Google Scholar
- S. Wolfram. The Mathematica Book, Third Edition. Cambridge University Press, Cambridge/MA, 1996.Google Scholar