{"type":"ScholarlyArticle","title":"Efficient Inference for Untied MLNs","authors":[{"name":"Somdeb Sarkhel","slug":"somdeb-sarkhel","given":"Somdeb","family":"Sarkhel","affiliation":"Adobe Research , San Jose , CA; Department of Computer Science , The University of Texas at Dallas"},{"name":"Deepak Venugopal","slug":"deepak-venugopal","given":"Deepak","family":"Venugopal","affiliation":"Department of Computer Science , The University of Memphis"},{"name":"Nicholas Ruozzi","slug":"nicholas-ruozzi","given":"Nicholas","family":"Ruozzi","affiliation":"Department of Computer Science , The University of Texas at Dallas"},{"name":"Vibhav Gogate","slug":"vibhav-gogate","given":"Vibhav","family":"Gogate","affiliation":"Department of Computer Science , The University of Texas at Dallas"}],"abstract":"We address the problem of scaling up local-search or sampling-based inference in Markov logic networks (MLNs) that have large shared sub-structures but no (or few) tied weights. Such untied MLNs are ubiquitous in practical applications. However, they have very few symmetries, and as a result lifted inference algorithms--the dominant approach for scaling up inference--perform poorly on them. The key idea in our approach is to reduce the hard, time-consuming sub-task in sampling algorithms, computing the sum of weights of features that satisfy a full assignment, to the problem of computing a set of partition functions of graphical models, each defined over the logical variables in a first-order formula. The importance of this reduction is that when the treewidth of all the graphical models is small, it yields an order of magnitude speedup. When the treewidth is large, we propose an over-symmetric approximation and experimentally demonstrate that it is both fast and accurate.","doi":"10.24963/ijcai.2017/644","url":"https://ijcai.org/proceedings/2017/644","pdf":"https://ijcai.org/proceedings/2017/0644.pdf","markdown":"https://ijcai.org/proceedings/2017/644.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/644","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Uncertainty in AI","track":"Main track","number":644,"pages":{"first":4617,"last":4624},"keywords":["Uncertainty in AI: Graphical Models","Uncertainty in AI: Relational Inference","Uncertainty in AI: Approximate Probabilistic Inference"],"videos":[],"references":[{"position":1,"raw":"[Chen et al., 2013] Chao Chen, Vladimir Kolmogorov, Yan Zhu, Dimitris Metaxas, and Christoph Lampert. Comput- ing the m most probable modes of a graphical model. In Proceedings of the 16th International Conference on Arti- ficial Intelligence and Statistics (AISTATS-13), 2013.","title":"Comput-ing the m most probable modes of a graphical model","authors":"Chao Chen, Vladimir Kolmogorov, Yan Zhu, Dimitris Metaxas, Christoph Lampert","year":"2013","venue":"Proceedings of the 16th International Conference on Artificial Intelligence and Statistics (AISTATS-13)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Das et al., 2016] Mayukh Das, Yuqing Wu, Tushar Khot, Kristian Kersting, and Sriraam Natarajan. Scaling lifted probabilistic inference and learning via graph databases. In SIAM International Conference on Data Mining, 2016.","title":"Scaling lifted probabilistic inference and learning via graph databases","authors":"Mayukh Das, Yuqing Wu, Tushar Khot, Kristian Kersting, Sriraam Natarajan","year":"2016","venue":"SIAM International Conference on Data Mining","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Domingos and Lowd, 2009] P. Domingos and D. Lowd. Markov Logic: An Interface Layer for Artificial Intelli- gence. Morgan & Claypool, San Rafael, CA, 2009.","title":"Markov Logic: An Interface Layer for Artificial Intelligence","authors":"P Domingos, D Lowd","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gelman and Rubin, 1992] A. Gelman and D. B. Rubin. In- ference from Iterative Simulation Using Multiple Se- quences. Statistical Science, 7(4):457-472, 1992.","title":"Inference from Iterative Simulation Using Multiple Sequences","authors":"A Gelman, D B Rubin","year":"1992","venue":"Statistical Science","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Genesereth and Kao, 2013] Michael R. Genesereth and Eric Kao. Introduction to Logic, Second Edition. Morgan & Claypool Publishers, 2013.","title":"Introduction to Logic, Second Edition","authors":"R Michael, Eric Genesereth, Kao","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gogate and Domingos, 2011] V. Gogate and P. Domingos. Probabilistic Theorem Proving. In Proceedings of the Twenty-Seventh Conference on Uncertainty in Artificial Intelligence, pages 256-265. AUAI Press, 2011.","title":"Probabilistic Theorem Proving","authors":"V Gogate, P Domingos","year":"2011","venue":"Proceedings of the Twenty-Seventh Conference on Uncertainty in Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hartigan, 1972] John A Hartigan. Direct clustering of a data matrix. Journal of the american statistical association, 67(337):123-129, 1972.","title":"Direct clustering of a data matrix","authors":"John A Hartigan","year":"1972","venue":"Journal of the american statistical association","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kautz et al., 1997] H. Kautz, B. Selman, and Y. Jiang. A General Stochastic Approach to Solving Problems with Hard and Soft Constraints. In D. Gu, J. Du, and P. Parda- los, editors, The Satisfiability Problem: Theory and Appli- cations, pages 573-586. American Mathematical Society, New York, NY, 1997.","title":"A General Stochastic Approach to Solving Problems with Hard and Soft Constraints","authors":"H Kautz, B Selman, Y Jiang","year":"1997","venue":"The Satisfiability Problem: Theory and Applications","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kersting et al., 2010] K. Kersting, Y. E. Massaoudi, F. Hadiji, and B. Ahmadi. Informed Lifting for Message- Passing. In Maria Fox and David Poole, editors, Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence, pages 1181-1186, 2010.","title":"Informed Lifting for Message-Passing","authors":"K Kersting, Y E Massaoudi, F Hadiji, B Ahmadi","year":"2010","venue":"Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lauritzen and Spiegelhalter, 1988] S. L. Lauritzen and D. J. Spiegelhalter. Local Computations with Probabilities on Graphical Structures and Their Application to Expert Sys- tems. Journal of the Royal Statistical Society. Series B (Methodological), 50(2):157-224, 1988.","title":"Local Computations with Probabilities on Graphical Structures and Their Application to Expert Systems","authors":"S L Lauritzen, D J Spiegelhalter","year":"1988","venue":"Journal of the Royal Statistical Society. Series B (Methodological)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Riedel and McCallum, 2011] Sebastian Riedel and Andrew McCallum. Robust biomedical event extraction with dual decomposition and minimal domain adaptation. In Pro- ceedings of the BioNLP Shared Task 2011 Workshop, pages 46-50, 2011.","title":"Robust biomedical event extraction with dual decomposition and minimal domain adaptation","authors":"Mccallum Riedel, Sebastian Riedel, Andrew Mccallum","year":"2011","venue":"Proceedings of the BioNLP Shared Task 2011 Workshop","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Sarkhel et al., 2016] Somdeb Sarkhel, Deepak Venugopal, Tuan Anh Pham, Parag Singla, and Vibhav Gogate. Scal- able training of markov logic networks using approximate counting. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016.","title":"Scalable training of markov logic networks using approximate counting","authors":"Sarkhel","year":"2016","venue":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Shavlik and Natarajan, 2009] Jude W. Shavlik and Sriraam Natarajan. Speeding up inference in markov logic net- works by preprocessing to reduce the size of the result- ing grounded network. In Proceedings of the 21st Inter- national Joint Conference on Artificial Intelligence, pages 1951-1956, 2009.","title":"Speeding up inference in markov logic networks by preprocessing to reduce the size of the resulting grounded network","authors":"Natarajan ; ] Shavlik, W Jude, Sriraam Shavlik, Natarajan","year":"2009","venue":"Proceedings of the 21st International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2009/322"},{"position":14,"raw":"[Singla and Domingos, 2006a] P. Singla and P. Domingos. Entity Resolution with Markov Logic. In Proceedings of the Sixth IEEE International Conference on Data Mining, pages 572-582, Hong Kong, 2006. IEEE Computer Soci- ety Press.","title":"Entity Resolution with Markov Logic","authors":"Domingos Singla, P Singla, P Domingos","year":"2006","venue":"Proceedings of the Sixth IEEE International Conference on Data Mining","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Singla and Domingos, 2006b] P. Singla and P. Domingos. Memory-Efficient Inference in Relational Domains. In Proceedings of the Twenty-First National Conference on Artificial Intelligence, Boston, MA, 2006. AAAI Press. This volume.","title":"Memory-Efficient Inference in Relational Domains","authors":"Domingos Singla, P Singla, P Domingos","year":"2006","venue":"Proceedings of the Twenty-First National Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Singla et al., 2014] Parag Singla, Aniruddh Nath, and Pedro Domingos. Approximate lifting techniques for belief prop- agation. In Proceedings of the Twenty-Eigth AAAI Confer- ence on Artificial Intelligence, pages 2497-2504, 2014.","title":"Approximate lifting techniques for belief propagation","authors":"Parag Singla, Aniruddh Nath, Pedro Domingos","year":"2014","venue":"Proceedings of the Twenty-Eigth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Tran and Davis, 2008] Son D. Tran and Larry S. Davis. Event modeling and recognition using markov logic net- works. In 10th European Conference on Computer Vision, pages 610-623, 2008.","title":"Event modeling and recognition using markov logic networks","authors":"Son D Tran, Larry S Davis","year":"2008","venue":"10th European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Van den Broeck and Darwiche, 2013] G. Van den Broeck and Adnan Darwiche. On the complexity and approxima- tion of binary evidence in lifted inference. In Proceedings of the Twenty-Seventh Annual Conference on Neural In- formation Processing Systems (NIPS), pages 2868-2876, 2013.","title":"On the complexity and approximation of binary evidence in lifted inference","authors":"Broeck Van Den, ] G Darwiche, Adnan Van Den Broeck, Darwiche","year":"2013","venue":"Proceedings of the Twenty-Seventh Annual Conference on Neural Information Processing Systems (NIPS)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Van den Broeck et al., 2012] G. Van den Broeck, A. Choi, and A. Darwiche. Lifted relax, compensate and then re- cover: From approximate to exact lifted probabilistic in- ference. In Proceedings of the Twenty-Eigth Conference on Uncertainty in Artificial Intelligence, pages 131-141, 2012.","title":"Lifted relax, compensate and then recover: From approximate to exact lifted probabilistic inference","authors":"Broeck Van Den","year":"2012","venue":"Proceedings of the Twenty-Eigth Conference on Uncertainty in Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Venugopal and Gogate, 2014] D. Venugopal and V. Gogate. Evidence-based Clustering for Scalable Inference in Markov Logic. In Machine Learning and Knowledge Dis- covery in Databases. 2014.","title":"Evidence-based Clustering for Scalable Inference in Markov Logic","authors":"D Venugopal, V Gogate","year":"2014","venue":"Machine Learning and Knowledge Discovery in Databases","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Venugopal et al., 2014] Deepak Venugopal, Chen Chen, Vibhav Gogate, and Vincent Ng. Relieving the computa- tional bottleneck: Joint inference for event extraction with high-dimensional features. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 831-843. ACL, 2014.","title":"Relieving the computational bottleneck: Joint inference for event extraction with high-dimensional features","authors":"Deepak Venugopal, Chen Chen, Vibhav Gogate, Vincent Ng","year":"2014","venue":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Venugopal et al., 2015] Deepak Venugopal, Somdeb Sarkhel, and Vibhav Gogate. Just count the satisfied groundings: Scalable local-search and sampling based inference in mlns. In Proceedings of the Twenty-Nineth AAAI Conference on Artificial Intelligence, pages 3606-3612, 2015.","title":"Just count the satisfied groundings: Scalable local-search and sampling based inference in mlns","authors":"Deepak Venugopal, Somdeb Sarkhel, Vibhav Gogate","year":"2015","venue":"Proceedings of the Twenty-Nineth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Venugopal et al., 2016] D. Venugopal, S. Sarkhel, and V. Gogate. Magician: Scalable Inference and Learn- ing in Markov logic using Approximate Symmetries. Technical report, Department of Computer Science, The University of Memphis, Memphis, TN, 2016. https://github.com/dvngp/CD-Learn.","title":"Magician: Scalable Inference and Learning in Markov logic using Approximate Symmetries","authors":"D Venugopal, S Sarkhel, V Gogate","year":"2016","venue":null,"doi":null,"url":"https://github.com/dvngp/CD-Learn","internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}