{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:00:08Z","timestamp":1781146808726,"version":"3.54.1"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372116"],"award-info":[{"award-number":["62372116"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neunet.2026.108974","type":"journal-article","created":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T08:27:37Z","timestamp":1775896057000},"page":"108974","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Causal discovery by continuous optimization with weighted superstructure"],"prefix":"10.1016","volume":"201","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2182-0207","authenticated-orcid":false,"given":"Mingjie","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yewei","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5544-5347","authenticated-orcid":false,"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4772-3284","authenticated-orcid":false,"given":"Ruxin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1958-8612","authenticated-orcid":false,"given":"Yuzhong","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2313-7635","authenticated-orcid":false,"given":"Jihong","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1949-2768","authenticated-orcid":false,"given":"Shuigeng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108974_bib0001","series-title":"Advances in neural information processing systems","first-page":"10119","article-title":"Recursive causal structure learning in the presence of latent variables and selection bias","volume":"vol. 34","author":"Akbari","year":"2021"},{"key":"10.1016\/j.neunet.2026.108974_bib0002","series-title":"Advances in neural information processing systems","first-page":"63945","article-title":"Fast scalable and accurate discovery of DAGs using the best order score search and grow shrink trees","volume":"vol. 36","author":"Andrews","year":"2023"},{"key":"10.1016\/j.neunet.2026.108974_bib0003","series-title":"Advances in neural information processing systems","first-page":"8226","article-title":"DAGMA: Learning dags via m-matrices and a log-determinant acyclicity characterization","volume":"vol. 35","author":"Bello","year":"2022"},{"key":"10.1016\/j.neunet.2026.108974_bib0004","series-title":"Advances in neural information processing systems","first-page":"21865","article-title":"Differentiable causal discovery from interventional data","volume":"vol. 33","author":"Brouillard","year":"2020"},{"issue":"6","key":"10.1016\/j.neunet.2026.108974_bib0005","doi-asserted-by":"crossref","first-page":"2526","DOI":"10.1214\/14-AOS1260","article-title":"CAM: Causal additive models, high-dimensional order search and penalized regression","volume":"42","author":"B\u00fchlmann","year":"2014","journal-title":"The Annals of Statistics"},{"key":"10.1016\/j.neunet.2026.108974_bib0006","first-page":"507","article-title":"Optimal structure identification with greedy search","volume":"3","author":"Chickering","year":"2003","journal-title":"Journal of Machine Learning Research : JMLR"},{"issue":"1","key":"10.1016\/j.neunet.2026.108974_bib0007","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1214\/11-AOS940","article-title":"Learning high-dimensional directed acyclic graphs with latent and selection variables","volume":"40","author":"Colombo","year":"2012","journal-title":"The Annals of Statistics"},{"key":"10.1016\/j.neunet.2026.108974_bib0008","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1162\/tacl_a_00511","article-title":"Causal inference in natural language processing: Estimation, prediction, interpretation and beyond","volume":"10","author":"Feder","year":"2022","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"4","key":"10.1016\/j.neunet.2026.108974_bib0009","doi-asserted-by":"crossref","first-page":"88:1","DOI":"10.1145\/3639048","article-title":"Causal inference in recommender systems: A survey and future directions","volume":"42","author":"Gao","year":"2024","journal-title":"ACM Transactions on Information Systems"},{"key":"10.1016\/j.neunet.2026.108974_bib0010","series-title":"Proceedings of the 37th international conference on machine learning","first-page":"3494","article-title":"Characterizing distribution equivalence and structure learning for cyclic and acyclic directed graphs","volume":"vol. 119","author":"Ghassami","year":"2020"},{"key":"10.1016\/j.neunet.2026.108974_bib0011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/JBHI.2025.3590391","article-title":"Cyclic contrastive representation learning for incomplete multi-modal medical image segmentation","author":"He","year":"2025","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"10.1016\/j.neunet.2026.108974_bib0012","series-title":"Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining","first-page":"596","article-title":"Daring: Differentiable causal discovery with residual independence","author":"He","year":"2021"},{"key":"10.1016\/j.neunet.2026.108974_bib0013","series-title":"Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining","first-page":"1551","article-title":"Generalized score functions for causal discovery","author":"Huang","year":"2018"},{"key":"10.1016\/j.neunet.2026.108974_bib0014","series-title":"2017\u202fIEEE International conference on data mining (ICDM)","first-page":"913","article-title":"Behind distribution shift: Mining driving forces of changes and causal arrows","author":"Huang","year":"2017"},{"key":"10.1016\/j.neunet.2026.108974_bib0015","series-title":"International conference on learning representations","article-title":"Gradient-based neural DAG learning","author":"Lachapelle","year":"2020"},{"key":"10.1016\/j.neunet.2026.108974_bib0016","series-title":"The thirty-ninth annual conference on neural information processing systems","article-title":"Local learning for covariate selection in nonparametric causal effect estimation with latent variables","author":"Li","year":"2025"},{"key":"10.1016\/j.neunet.2026.108974_bib0017","series-title":"Proceedings of the KDD\u201921 workshop on causal discovery","first-page":"26","article-title":"A recursive markov boundary-based approach to causal structure learning","volume":"vol. 150","author":"Mokhtarian","year":"2021"},{"issue":"61","key":"10.1016\/j.neunet.2026.108974_bib0018","first-page":"1","article-title":"Recursive causal discovery","volume":"26","author":"Mokhtarian","year":"2025","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.neunet.2026.108974_bib0019","series-title":"Advances in neural information processing systems","first-page":"17943","article-title":"On the role of sparsity and DAG constraints for learning linear DAGs","volume":"vol. 33","author":"Ng","year":"2020"},{"key":"10.1016\/j.neunet.2026.108974_bib0020","series-title":"Proceedings of the 25th international conference on artificial intelligence and statistics","first-page":"8176","article-title":"On the convergence of continuous constrained optimization for structure learning","volume":"vol. 151","author":"Ng","year":"2022"},{"key":"10.1016\/j.neunet.2026.108974_bib0021","series-title":"Advances in neural information processing systems","first-page":"20308","article-title":"Reliable causal discovery with improved exact search and weaker assumptions","volume":"vol. 34","author":"Ng","year":"2021"},{"key":"10.1016\/j.neunet.2026.108974_bib0022","unstructured":"Ng, I., Zhu, S., Chen, Z., & Fang, Z. (2019). A graph autoencoder approach to causal structure learning. arXiv: 1911.07420,."},{"key":"10.1016\/j.neunet.2026.108974_bib0023","series-title":"Proceedings of the 2022\u202fSIAM international conference on data mining (SDM)","first-page":"424","article-title":"Masked gradient-based causal structure learning","author":"Ng","year":"2022"},{"key":"10.1016\/j.neunet.2026.108974_bib0024","series-title":"Numerical optimization","author":"Nocedal","year":"1999"},{"key":"10.1016\/j.neunet.2026.108974_bib0025","series-title":"Proceedings of the eighth international conference on probabilistic graphical models","first-page":"368","article-title":"A hybrid causal search algorithm for latent variable models","volume":"vol. 52","author":"Ogarrio","year":"2016"},{"key":"10.1016\/j.neunet.2026.108974_bib0026","series-title":"Proceedings of the twenty third international conference on artificial intelligence and statistics","first-page":"1595","article-title":"DYNOTEARS: Structure learning from time-series data","volume":"vol. 108","author":"Pamfil","year":"2020"},{"key":"10.1016\/j.neunet.2026.108974_bib0027","series-title":"Causality: Models, reasoning and inference","author":"Pearl","year":"2009"},{"key":"10.1016\/j.neunet.2026.108974_bib0028","series-title":"The book of why: The new science of cause and effect","author":"Pearl","year":"2018"},{"issue":"1","key":"10.1016\/j.neunet.2026.108974_bib0029","first-page":"2009","article-title":"Causal discovery with continuous additive noise models","volume":"15","author":"Peters","year":"2014","journal-title":"Journal of Machine Learning Research : JMLR"},{"issue":"2","key":"10.1016\/j.neunet.2026.108974_bib0030","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/s41060-016-0032-z","article-title":"A million variables and more: The fast greedy equivalence search algorithm for learning high-dimensional graphical causal models, with an application to functional magnetic resonance images","volume":"3","author":"Ramsey","year":"2017","journal-title":"International Journal of Data Science and Analytics"},{"key":"10.1016\/j.neunet.2026.108974_bib0031","series-title":"Proceedings of the twenty-second conference on uncertainty in artificial intelligence","first-page":"401","article-title":"Adjacency-faithfulness and conservative causal inference","author":"Ramsey","year":"2006"},{"key":"10.1016\/j.neunet.2026.108974_bib0032","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2025.104391","article-title":"Regression-based conditional independence test with adaptive kernels","volume":"347","author":"Ren","year":"2025","journal-title":"Artificial Intelligence"},{"issue":"5721","key":"10.1016\/j.neunet.2026.108974_bib0033","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1126\/science.1105809","article-title":"Causal protein-signaling networks derived from multiparameter single-cell data","volume":"308","author":"Sachs","year":"2005","journal-title":"Science"},{"issue":"14","key":"10.1016\/j.neunet.2026.108974_bib0034","doi-asserted-by":"crossref","first-page":"2441","DOI":"10.1093\/bioinformatics\/bty1005","article-title":"Accurate and efficient estimation of small P-values with the cross-entropy method: Applications in genomic data analysis","volume":"35","author":"Shi","year":"2018","journal-title":"Bioinformatics"},{"key":"10.1016\/j.neunet.2026.108974_bib0035","first-page":"2003","article-title":"A linear non-gaussian acyclic model for causal discovery","volume":"7","author":"Shimizu","year":"2006","journal-title":"Journal of Machine Learning Research : JMLR"},{"issue":"4","key":"10.1016\/j.neunet.2026.108974_bib0036","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1093\/biomet\/asaa104","article-title":"Consistency guarantees for greedy permutation-based causal inference algorithms","volume":"108","author":"Solus","year":"2021","journal-title":"Biometrika"},{"issue":"1","key":"10.1016\/j.neunet.2026.108974_bib0037","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1177\/089443939100900106","article-title":"An algorithm for fast recovery of sparse causal graphs","volume":"9","author":"Spirtes","year":"1991","journal-title":"Social Science Computer Review"},{"key":"10.1016\/j.neunet.2026.108974_bib0038","series-title":"Causation, prediction, and search","author":"Spirtes","year":"2001"},{"key":"10.1016\/j.neunet.2026.108974_bib0039","series-title":"Proceedings of the 26th international conference on artificial intelligence and statistics","first-page":"1942","article-title":"NTS-notears: Learning nonparametric dbns with prior knowledge","volume":"vol. 206","author":"Sun","year":"2023"},{"issue":"1","key":"10.1016\/j.neunet.2026.108974_bib0040","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/s10994-006-6889-7","article-title":"The max-min hill-climbing Bayesian network structure learning algorithm","volume":"65","author":"Tsamardinos","year":"2006","journal-title":"Machine Learning"},{"key":"10.1016\/j.neunet.2026.108974_bib0041","series-title":"Advances in neural information processing systems","first-page":"3895","article-title":"Dags with no fears: A closer look at continuous optimization for learning Bayesian networks","volume":"vol. 33","author":"Wei","year":"2020"},{"key":"10.1016\/j.neunet.2026.108974_bib0042","series-title":"2023\u202fIEEE International conference on data mining (ICDM)","first-page":"668","article-title":"Causal discovery by continuous optimization with conditional independence constraint: Methodology and performance","author":"Xia","year":"2023"},{"key":"10.1016\/j.neunet.2026.108974_bib0043","series-title":"Proceedings of the 36th international conference on machine learning","first-page":"7154","article-title":"DAG-GNN: DAG structure learning with graph neural networks","volume":"vol. 97","author":"Yu","year":"2019"},{"key":"10.1016\/j.neunet.2026.108974_bib0044","series-title":"The eleventh international conference on learning representations","article-title":"Boosting causal discovery via adaptive sample reweighting","author":"Zhang","year":"2023"},{"issue":"12","key":"10.1016\/j.neunet.2026.108974_bib0045","doi-asserted-by":"crossref","first-page":"10259","DOI":"10.1109\/TPAMI.2024.3435503","article-title":"Towards effective causal partitioning by edge cutting of adjoint graph","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.108974_bib0046","series-title":"Proceedings of the thirty-first AAAI conference on artificial intelligence","first-page":"1250","article-title":"Causal discovery using regression-based conditional independence tests","author":"Zhang","year":"2017"},{"key":"10.1016\/j.neunet.2026.108974_bib0047","series-title":"Proceedings of the 26th international joint conference on artificial intelligence","first-page":"1347","article-title":"Causal discovery from nonstationary\/heterogeneous data: Skeleton estimation and orientation determination","author":"Zhang","year":"2017"},{"key":"10.1016\/j.neunet.2026.108974_bib0048","series-title":"Proceedings of the twenty-seventh conference on uncertainty in artificial intelligence","first-page":"804","article-title":"Kernel-based conditional independence test and application in causal discovery","author":"Zhang","year":"2011"},{"key":"10.1016\/j.neunet.2026.108974_bib0049","series-title":"Advances in neural information processing systems","first-page":"18390","article-title":"Truncated matrix power iteration for differentiable DAG learning","volume":"vol. 35","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108974_bib0050","series-title":"Proceedings of the 32nd international conference on neural information processing systems","first-page":"9492","article-title":"Dags with no tears: Continuous optimization for structure learning","author":"Zheng","year":"2018"},{"key":"10.1016\/j.neunet.2026.108974_bib0051","series-title":"Proceedings of the twenty third international conference on artificial intelligence and statistics","first-page":"3414","article-title":"Learning sparse nonparametric DAGs","volume":"vol. 108","author":"Zheng","year":"2020"},{"key":"10.1016\/j.neunet.2026.108974_bib0052","series-title":"International conference on learning representations","article-title":"Causal discovery with reinforcement learning","author":"Zhu","year":"2020"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004351?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026004351?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T02:55:15Z","timestamp":1781146515000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026004351"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":52,"alternative-id":["S0893608026004351"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108974","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Causal discovery by continuous optimization with weighted superstructure","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108974","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108974"}}