{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T06:08:13Z","timestamp":1768457293901,"version":"3.49.0"},"reference-count":40,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":59,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12071308"],"award-info":[{"award-number":["12071308"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2022J02050"],"award-info":[{"award-number":["2022J02050"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>Exact inference for large, directed graphical models, also known as Bayesian networks (BNs), can be intractable as the space complexity grows exponentially in the tree\u2010width of the model. Approximate inference, such as generalized belief propagation (GBP), is used instead. GBP treats inference as the Bethe\/Kikuchi energy function optimization problem. The solution is found using iterative message passing, which is inefficient and convergent problematic. Recent progress on amortized technique for GBP is an attractive alternative solution that can optimize the Bethe\/Kikuchi energy function using (deep) neural networks, requiring no message passing. Despite being efficient, the amortized technique for GBP is applied to undirected graphical models with specific structures and factors, with no guarantee of the approximation quality. This is because the energy function to be amortized is defined by a region (or factor) graph that is ad hoc and difficult to construct to ensure sensible approximations. This paper proposes a new amortized GBP algorithm applied to BN for efficient inference. The proposed algorithm is composed of the following: (i) a new pairwise conversion (PWC) algorithm that converts all the conditional probability distributions in the BN into pairwise factors to facilitate efficient region graph constructions; (ii) following PWC, an improved loop structured region graph (LSRG) algorithm was derived to generate a valid region graph satisfying desired regional properties; and (iii) the energy function defined by the proposed PWC\u2010LSRG region graph can be directly amortized using (deep) neural networks to ensure sensible approximations. Empirical studies show that the proposed amortized PWC\u2010LSRG algorithm is of practical use and significantly improves convergence and efficiency compared to conventional algorithms.<\/jats:p>","DOI":"10.1155\/2023\/2131915","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T22:35:07Z","timestamp":1677710107000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Performing Bayesian Network Inference Using Amortized Region Approximation with Graph Factorization"],"prefix":"10.1155","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7589-3160","authenticated-orcid":false,"given":"Peng","family":"Lin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8027-3572","authenticated-orcid":false,"given":"Changsheng","family":"Dou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6938-5338","authenticated-orcid":false,"given":"Nannan","family":"Gu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7073-2245","authenticated-orcid":false,"given":"Zhiyuan","family":"Shi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0188-7259","authenticated-orcid":false,"given":"Lili","family":"Ma","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2023,3]]},"reference":[{"key":"e_1_2_9_1_2","volume-title":"Probabilistic Graphical Models - Principles and Techniques","author":"Koller D.","year":"2009"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.1097\/mjt.0000000000001450"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1017\/s1748499514000098"},{"key":"e_1_2_9_5_2","unstructured":"ElidanG. University of Hebrew bayesian network repository 2022 https:\/\/www.cs.huji.ac.il\/w%7Egalel\/Repository\/."},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2019.101659"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.1201\/b21982"},{"key":"e_1_2_9_8_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1988.tb01721.x"},{"key":"e_1_2_9_9_2","volume-title":"Variational Algorithms for Approximate Bayesian Inference [Ph.D]: The Gatsby Computational Neuroscience Unit","author":"Beal M. J.","year":"2003"},{"key":"e_1_2_9_10_2","unstructured":"HoffmanM.andBleiD. Stochastic structured variational inference Proceedings of the 18th International Conference on Artificial Intelligence and Statistics PMLR May 2015 San Diego CA USA 361\u2013369."},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2005.850085"},{"key":"e_1_2_9_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9018-y"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2842"},{"key":"e_1_2_9_14_2","unstructured":"GelfandA.andWellingM. Generalized belief propagation on tree robust structured region graphs Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence August 2012 Catalina Island CA 296\u2013305."},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12198"},{"key":"e_1_2_9_16_2","unstructured":"MasegosaA. R. MartinezA. M. andLangsethH. Distributed variational message passing Proceedings of the 8th International Conference on Probabilistic Graphical Models PMLR September 2016 Lugano Switzerland 321\u2013332."},{"key":"e_1_2_9_17_2","doi-asserted-by":"publisher","DOI":"10.1162\/08997660360581958"},{"key":"e_1_2_9_18_2","doi-asserted-by":"publisher","DOI":"10.3390\/e23010117"},{"key":"e_1_2_9_19_2","volume-title":"Advances in Neural Information Processing Systems","author":"Johnson M. J.","year":"2016"},{"key":"e_1_2_9_20_2","unstructured":"LiC. WellingM. ZhuJ. andZhangB. Graphical generative adversarial networks Proceedings of the 32nd International Conference on Neural Information Processing Systems December 2018 Montr\u00e9al Canada 6069\u20136080."},{"key":"e_1_2_9_21_2","unstructured":"KingmaD. P.andWellingM. BengioY.andLeCunY. Auto-encoding variational Bayes Proceedings of the 2nd International Conference on Learning Representations April 2014 Banff AB Canada 1\u201314."},{"key":"e_1_2_9_22_2","unstructured":"GershmanS.andGoodmanN. Amortized inference in probabilistic reasoning Proceedings of the Annual Meeting of the Cognitive Science Society July 2014 Quebec City QC Canada 517\u2013522."},{"key":"e_1_2_9_23_2","unstructured":"MnihA.andGregorK. XingE. P. Neural variational inference and learning in belief networks Proceedings of the 31st International Conference on Machine Learning June 2014 Beijing China 1791\u20131799."},{"key":"e_1_2_9_24_2","unstructured":"YoonK. LiaoR. andXiongY. Inference in probabilistic graphical models by graph neural networks Proceedings of the 6th International Conference on Learning Representations (ICLR) workshop May 2018 Vancouver Canada."},{"key":"e_1_2_9_25_2","unstructured":"ZhangZ. WuF. andLeeW. S. Factor graph neural network Proceedings of the 34th Conference on Neural Information Processing Systems December 2020 8577\u20138587."},{"key":"e_1_2_9_26_2","unstructured":"FeiY.andPitkowX. Generalization of graph network inferences in higher-order probabilistic graphical models 2021 https:\/\/arxiv.org\/abs\/2107.05729."},{"key":"e_1_2_9_27_2","unstructured":"SrikumarV. KunduG. andRothD. On amortizing inference cost for structured prediction Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning July 2012 Jeju Island Korea Association for Computational Linguistics 1114\u20131124."},{"key":"e_1_2_9_28_2","unstructured":"WisemanS.andKimY. Amortized bethe free energy minimization for learning mrfs Proceedings of the 33rd Conference on Neural Information Processing Systems December 2019."},{"key":"e_1_2_9_29_2","unstructured":"LiuD. ThobabenR. andRasmussenL. K. Region-based energy neural network for approximate inference 2020 https:\/\/arxiv.org\/abs\/2006.09927."},{"key":"e_1_2_9_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20096-0_5"},{"key":"e_1_2_9_31_2","unstructured":"PearlJ. WaltzD. Reverend Bayes on inference engines: a distributed hierarchical approach Proceedings of the Second National Conference on Artificial Intelligence Aaai-82 August 1982 Pittsburgh Pennsylvania PA USA AAAI Press."},{"key":"e_1_2_9_32_2","doi-asserted-by":"publisher","DOI":"10.1002\/int.22973"},{"key":"e_1_2_9_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2011.87"},{"key":"e_1_2_9_34_2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000001"},{"key":"e_1_2_9_35_2","unstructured":"Agena AgenaRisk 2022 https:\/\/www.agenarisk.com."},{"key":"e_1_2_9_36_2","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_37_2","unstructured":"PaszkeA. GrossS. andChintalaS. Automatic differentiation in PyTorch Proceedings of the NIPS 2017 Workshop on Autodiff December 2017 Long Beach California."},{"key":"e_1_2_9_38_2","unstructured":"den BroeckG. V. MohanK. ChoiA. andPearlJ. Efficient algorithms for bayesian network parameter learning from incomplete data Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence July 2015 Amsterdam Netherlands 161\u2013170."},{"key":"e_1_2_9_39_2","unstructured":"LinP. Data repository: amortized BN inference 2022 https:\/\/github.com\/penglin17\/amortizedBNinference."},{"key":"e_1_2_9_40_2","first-page":"239","article-title":"A model-based approach to insulin adjustment","volume":"6","author":"Andreassen S.","year":"1991","journal-title":"Proceedings of the Third Conference on Artificial Intelligence in Medicine"}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/2131915.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijis\/2023\/2131915.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2023\/2131915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T05:32:35Z","timestamp":1735623155000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2023\/2131915"}},"subtitle":[],"editor":[{"given":"Subrata Kumar","family":"Sarker","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1155\/2023\/2131915"],"URL":"https:\/\/doi.org\/10.1155\/2023\/2131915","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"2022-09-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-03-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2131915"}}