On Triangulating Dynamic Graphical Models

This paper introduces improved methodology to triangulate dynamic graphical models and dynamic Bayesian networks (DBNs). In this approach, a standard DBN template can be modified so the repeating and unrolled graph section may dissect the original DBN time slice and may also span (and partially intersect) many such slices. We introduce the notion of a "boundary" which divides a graph into multi-slice partitions each of which has an interface, and define the "boundary algorithm", a method to find the best boundary (and corresponding interface) between partitions in such models. We prove that, after using this algorithm, the sizes of the best forwardand backward- interface (and also the corresponding fill-ins) are identical. The boundary algorithm allows for constrained elimination orders (and therefore graph triangulations) that are impossible using standard slice-by-slice constrained elimination. We describe the above using the Graphical Model ToolKit (GMTK)'s notion of dynamic graphical model, slightly generalizing standard DBN templates. We report triangulation results on hand-concocted graphs, novel speech recognition DBNs, and random graphs, and find that the boundary algorithm can significantly improve both tree width and graph weight.

[1]  Fabio Gagliardi Cozman,et al.  Random Generation of Bayesian Networks , 2002, SBIA.

[2]  Michael C. Horsch,et al.  Dynamic Bayesian networks , 1990 .

[3]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

[4]  Adnan Darwiche,et al.  Constant-space reasoning in dynamic Bayesian networks , 2001, Int. J. Approx. Reason..

[5]  Geoffrey Zweig,et al.  Probabilistic modeling with Bayesian networks for automatic speech recognition , 1998, ICSLP.

[6]  Michael I. Jordan.  Graphical Models , 2003 .

[7]  D. Rose.  A GRAPH-THEORETIC STUDY OF THE NUMERICAL SOLUTION OF SPARSE POSITIVE DEFINITE SYSTEMS OF LINEAR EQUATIONS , 1972 .

[8]  David Madigan,et al.  Probabilistic Temporal Reasoning , 2005, Handbook of Temporal Reasoning in Artificial Intelligence.

[9]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

[10]  Zoubin Ghahramani,et al.  Learning Dynamic Bayesian Networks , 1997, Summer School on Neural Networks.

[11]  Uffe Kjærulff.  Optimal decomposition of probabilistic networks by simulated annealing , 1992 .

[12]  Uffe Kjærulff,et al.  dHugin: a computational system for dynamic time-sliced Bayesian networks , 1995 .

[13]  Jeff A. Bilmes,et al.  DBN based multi-stream models for speech , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[14]  Jeff A. Bilmes,et al.  The 2001 GMTK-based SPINE ASR system , 2002, INTERSPEECH.

[15]  Uue Kjjrull.  Dhugin: a Computational System for Dynamic Time-sliced Bayesian Networks E Dhugin: a Computational System for Dynamic Time-sliced Bayesian Networks , 1994 .

[16]  Kevin Murphy,et al.  Dynamic Bayesian Networks , 2002 .

[17]  Robert E. Tarjan,et al.  Algorithmic Aspects of Vertex Elimination on Graphs , 1976, SIAM J. Comput..

[18]  Uffe Kjærulff,et al.  A Computational Scheme for Reasoning in Dynamic Probabilistic Networks , 1992, UAI.

[19]  Geoffrey Zweig,et al.  The graphical models toolkit: An open source software system for speech and time-series processing , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[20]  Yang Xiang,et al.  Temporally Invariant Junction Tree for Inference in Dynamic Bayesian Network , 1998, Canadian Conference on AI.