Efficient Sequential Clamping for Lifted Message Passing
- 1.1k Downloads
Lifted message passing approaches can be extremely fast at computing approximate marginal probability distributions over single variables and neighboring ones in the underlying graphical model. They do, however, not prescribe a way to solve more complex inference tasks such as computing joint marginals for k-tuples of distant random variables or satisfying assignments of CNFs. A popular solution in these cases is the idea of turning the complex inference task into a sequence of simpler ones by selecting and clamping variables one at a time and running lifted message passing again after each selection. This naive solution, however, recomputes the lifted network in each step from scratch, therefore often canceling the benefits of lifted inference. We show how to avoid this by efficiently computing the lifted network for each conditioning directly from the one already known for the single node marginals. Our experiments show that significant efficiency gains are possible for lifted message passing guided decimation for SAT and sampling.
KeywordsRelational Probabilistic Models Relational Learning Probabilistic Inference Satisfiability
Unable to display preview. Download preview PDF.
- 1.Acar, U., Ihler, A., Mettu, R., Sumer, O.: Adaptive inference on general graphical models. In: Proc. of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence (UAI 2008). AUAI Press, Corvallis (2008)Google Scholar
- 4.Gomes, C.P., Hoffmann, J., Sabharwal, A., Selman, B.: From sampling to model counting. In: 20th IJCAI, Hyderabad, India, pp. 2293–2299 (January 2007)Google Scholar
- 6.Kersting, K., Ahmadi, B., Natarajan, S.: Counting belief propagation. In: Proc. of the 25th Conf. on Uncertainty in AI (UAI 2009), Montreal, Canada (2009)Google Scholar
- 7.Kschischang, F.R., Frey, B.J., Loeliger, H.-A.: Factor graphs and the sum-product algorithm. IEEE Transactions on Information Theory 47 (2001)Google Scholar
- 9.Milch, B., Zettlemoyer, L., Kersting, K., Haimes, M., Pack Kaelbling, L.: Lifted Probabilistic Inference with Counting Formulas. In: Proc. of the 23rd AAAI Conf. on Artificial Intelligence, AAAI 2008 (July 13–17, 2008)Google Scholar
- 10.Montanari, A., Ricci-Tersenghi, F., Semerjian, G.: Solving constraint satisfaction problems through belief propagation-guided decimation. In: Proc. of the 45th Allerton Conference on Communications, Control and Computing (2007)Google Scholar
- 11.Nath, A., Domingos, P.: Efficient lifting for online probabilistic inference. In: Proceedings of the Twenty-Fourth AAAI Conference on AI, AAAI 2010 (2010)Google Scholar
- 13.Richardson, M., Domingos, P.: Markov Logic Networks. MLJ 62, 107–136 (2006)Google Scholar
- 14.Selman, B., Kautz, H., Cohen, B.: Local search strategies for satisfiability testing. DIMACS Series in Discrete Mathematics and Theoretical Computer Science, pp. 521–532 (1995)Google Scholar
- 15.Sen, P., Deshpande, A., Getoor, L.: Bisimulation-based approximate lifted inference. In: Proc. of the 25th Conf. on Uncertainty in AI, UAI 2009 (2009)Google Scholar
- 16.Singla, P., Domingos, P.: Lifted First-Order Belief Propagation. In: Proc. of the 23rd AAAI Conf. on AI (AAAI 2008), pp. 1094–1099 (2008)Google Scholar