{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T12:12:15Z","timestamp":1779451935141,"version":"3.53.1"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["72573161"],"award-info":[{"award-number":["72573161"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72174180"],"award-info":[{"award-number":["72174180"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","award":["22JJD790080"],"award-info":[{"award-number":["22JJD790080"]}],"id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.knosys.2026.115774","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T16:03:59Z","timestamp":1773763439000},"page":"115774","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ACT: Anomaly-aware causal transformer with mixture-of-experts for time-series forecasting"],"prefix":"10.1016","volume":"341","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0417-7942","authenticated-orcid":false,"given":"Han","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9027-0674","authenticated-orcid":false,"given":"Yufeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5060-7092","authenticated-orcid":false,"given":"Xinyi","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115774_bib0001","series-title":"Advances in Neural Information Processing Systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"issue":"332","key":"10.1016\/j.knosys.2026.115774_bib0002","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.1080\/01621459.1970.10481180","article-title":"Distribution of residual autocorrelations in autoregressive-integrated moving average time series models","volume":"65","author":"Box","year":"1970","journal-title":"J. Am. Stat. Assoc."},{"issue":"3","key":"10.1016\/j.knosys.2026.115774_bib0003","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1016\/S0169-2070(01)00110-8","article-title":"A state space framework for automatic forecasting using exponential smoothing methods","volume":"18","author":"Hyndman","year":"2002","journal-title":"Int. J. Forecast."},{"key":"10.1016\/j.knosys.2026.115774_bib0004","series-title":"Advances in Neural Information Processing Systems","first-page":"155","article-title":"Support vector regression machines","author":"Drucker","year":"1997"},{"key":"10.1016\/j.knosys.2026.115774_bib0005","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"issue":"8","key":"10.1016\/j.knosys.2026.115774_bib0006","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.knosys.2026.115774_bib0007","doi-asserted-by":"crossref","unstructured":"K. Cho, B. Van Merri\u00ebnboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, Y. Bengio, Learning phrase representations using RNN encoder-decoder for statistical machine translation, arXiv preprint arXiv: 1406.1078(2014).","DOI":"10.3115\/v1\/D14-1179"},{"key":"10.1016\/j.knosys.2026.115774_bib0008","unstructured":"S. Bai, J.Z. Kolter, V. Koltun, An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, arXiv preprint arXiv: 1803.01271(2018)."},{"key":"10.1016\/j.knosys.2026.115774_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.117370","article-title":"China\u2019s commercial bank stock price prediction using a novel K-means-LSTM hybrid approach","volume":"202","author":"Chen","year":"2022","journal-title":"Expert Syst. Appl."},{"issue":"12","key":"10.1016\/j.knosys.2026.115774_bib0010","doi-asserted-by":"crossref","first-page":"13902","DOI":"10.1109\/TCYB.2021.3121312","article-title":"An accurate GRU-based power time-series prediction approach with selective state updating and stochastic optimization","volume":"52","author":"Zheng","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.knosys.2026.115774_bib0011","series-title":"AAAI Conference on Artificial Intelligence","first-page":"11106","article-title":"Informer: beyond efficient transformer for long sequence time-series forecasting","author":"Zhou","year":"2021"},{"key":"10.1016\/j.knosys.2026.115774_bib0012","article-title":"Graph-enhanced anomaly detection framework in multivariate time series using graph attention and enhanced generative adversarial networks","volume":"271","author":"Liu","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.115774_bib0013","unstructured":"Y. Liu, T. Hu, H. Xu, H. Wu, S. Wang, L. Ma, M. Long, iTransformer: Inverted-variate transformers for long-term time series forecasting, arXiv preprint arXiv: 2310.06625(2023)."},{"key":"10.1016\/j.knosys.2026.115774_bib0014","series-title":"International Conference on Learning Representations","article-title":"A time series is worth 64 words: long-term forecasting with transformers","author":"Nie","year":"2023"},{"key":"10.1016\/j.knosys.2026.115774_bib0015","series-title":"International Conference on Learning Representations","article-title":"TimeMixer: decomposable multiscale mixing for time series forecasting","author":"Wang","year":"2024"},{"key":"10.1016\/j.knosys.2026.115774_bib0016","article-title":"CCNN-Former: combining convolutional neural network and transformer for image-based traffic time series prediction","volume":"268","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.115774_bib0017","article-title":"Heterogeneous multivariate time series imputation by transformer model with missing position encoding","volume":"271","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.115774_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.110060","article-title":"Sparse temporal aware capsule network for robust speech emotion recognition","volume":"144","author":"Zhang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.115774_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114088","article-title":"PerioDformer: periodic disposition enhanced transformer for time series forecasting","volume":"327","author":"Tang","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115774_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113912","article-title":"Multivariate time series forecasting based on time\u2013frequency transform mixed convolution (DCWTNet)","volume":"325","author":"Dou","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115774_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113846","article-title":"CAWformer: A cross variable attention with discrete wavelet denoising for multivariate time series forecasting","volume":"324","author":"Fan","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115774_bib0022","first-page":"1","article-title":"Predictive deep reinforcement learning with multi-agent DQN for multivariate time series health monitoring","volume":"315","author":"Adegboye","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115774_bib0023","first-page":"1","article-title":"Reprogramming large language models for bitcoin price chart forecasting","volume":"317","author":"Chaffard","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115774_bib0024","first-page":"1","article-title":"Evolving graph convolutional network for multivariate time series forecasting","volume":"313","author":"Wang","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.115774_bib0025","doi-asserted-by":"crossref","first-page":"424","DOI":"10.2307\/1912791","article-title":"Investigating causal relations by econometric models and cross-spectral methods","volume":"37","author":"Granger","year":"1969","journal-title":"Econometrica J. Econom. Soc."},{"key":"10.1016\/j.knosys.2026.115774_bib0026","doi-asserted-by":"crossref","first-page":"1525","DOI":"10.1016\/j.eap.2025.10.025","article-title":"Marginal impact of European gas shocks on EU inflation variations: evidence from a TVP-SVAR-SV approach","volume":"88","author":"Chen","year":"2025","journal-title":"Econ. Anal. Policy"},{"key":"10.1016\/j.knosys.2026.115774_bib0027","article-title":"Applying time delay convergent cross mapping to Bitcoin time series","volume":"277","author":"Ausloos","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.115774_bib0028","series-title":"2019 IEEE\/ACM International Symposium on Quality of Service (IWQoS)","first-page":"1","article-title":"CoFlux: robustly correlating KPIs by fluctuations for service troubleshooting","author":"Su","year":"2019"},{"key":"10.1016\/j.knosys.2026.115774_bib0029","article-title":"Long-term forecasting with tiDE: time-series dense encoder","volume":"4","author":"Das","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.115774_bib0030","first-page":"5816","article-title":"SCINet: time series modeling and forecasting with sample convolution and interaction","volume":"35","author":"Liu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"8","key":"10.1016\/j.knosys.2026.115774_bib0031","first-page":"4267","article-title":"Neural Granger causality","volume":"44","author":"Tank","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"10.1016\/j.knosys.2026.115774_bib0032","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","volume":"3","author":"Jacobs","year":"1991","journal-title":"Neural Comput."},{"key":"10.1016\/j.knosys.2026.115774_bib0033","unstructured":"N. Shazeer, A. Mirhoseini, K. Maziarz, A. Davis, Q. Le, G. Hinton, J. Dean, Outrageously large neural networks: the sparsely-gated mixture-of-experts layer, arXiv preprint arXiv: 1701.06538(2017)."},{"key":"10.1016\/j.knosys.2026.115774_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.109312","article-title":"Demography-aware personalized federated learning for fair, private, and efficient clinical risk prediction","volume":"114","author":"Zhao","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.knosys.2026.115774_bib0035","series-title":"International Conference on Learning Representations","article-title":"Reversible instance normalization for deep learning-based time series forecasting","author":"Kim","year":"2021"},{"issue":"1","key":"10.1016\/j.knosys.2026.115774_bib0036","doi-asserted-by":"crossref","first-page":"2553","DOI":"10.1038\/s41467-019-10105-3","article-title":"Inferring causation from time series in Earth system sciences","volume":"10","author":"Runge","year":"2019","journal-title":"Nat. Commun."},{"key":"10.1016\/j.knosys.2026.115774_bib0037","first-page":"2003","article-title":"A linear non-Gaussian acyclic model for causal discovery","volume":"7","author":"Shimizu","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.115774_bib0038","series-title":"Advances in Neural Information Processing Systems","first-page":"22419","article-title":"AutoFormer: decomposition transformers with auto-correlation for long-term series forecasting","author":"Wu","year":"2021"},{"key":"10.1016\/j.knosys.2026.115774_bib0039","series-title":"Advances in Neural Information Processing Systems","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014"},{"key":"10.1016\/j.knosys.2026.115774_bib0040","unstructured":"N. Kitaev, \u0141. Kaiser, A. Levskaya, Reformer: The efficient Transformer, arXiv preprint arXiv: 2001.04451(2020)."},{"key":"10.1016\/j.knosys.2026.115774_bib0041","series-title":"The Eleventh International Conference on Learning Representations","article-title":"A time series is worth 64 words: long-term forecasting with transformers","author":"Nie","year":"2023"},{"key":"10.1016\/j.knosys.2026.115774_bib0042","series-title":"The Eleventh International Conference on Learning Representations","article-title":"TimesNet: temporal 2D-variation modeling for general time series analysis","author":"Wu","year":"2023"},{"key":"10.1016\/j.knosys.2026.115774_bib0043","unstructured":"F. Ye, T. Zhou, Z. Cheng, J. Peng, J. Zhang, G. Li, DUET: a DUal-core tEmporal-modeling Transformer for long-term time series forecasting, arXiv preprint arXiv: 2311.12117(2023)."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005009?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126005009?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T11:50:15Z","timestamp":1779450615000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126005009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":43,"alternative-id":["S0950705126005009"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115774","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ACT: Anomaly-aware causal transformer with mixture-of-experts for time-series forecasting","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115774","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115774"}}