{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T16:09:54Z","timestamp":1784995794910,"version":"3.55.0"},"reference-count":60,"publisher":"Association for Computing Machinery (ACM)","issue":"6","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>Many multivariate time series anomaly detection frameworks have been proposed and widely applied. However, most of these frameworks do not consider intrinsic relationships between variables in multivariate time series data, thus ignoring the causal relationship among variables and degrading anomaly detection performance. This work proposes a novel framework called CGAD, an entropy causal graph for multivariate time series Anomaly Detection. CGAD utilizes transfer entropy to construct graph structures that unveil the underlying causal relationships among time series data. Weighted graph convolutional networks combined with causal convolutions are employed to model both the causal graph structures and the temporal patterns within multivariate time series data. Furthermore, CGAD applies anomaly scoring, leveraging median absolute deviation-based normalization to improve the robustness of the anomaly identification process. Extensive experiments demonstrate that CGAD outperforms state-of-the-art methods on real-world datasets with a 9% average improvement in terms of three different multivariate time series anomaly detection metrics.<\/jats:p>","DOI":"10.1145\/3757922","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T22:09:12Z","timestamp":1754604552000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Entropy Causal Graphs for Multivariate Time Series Anomaly\u00a0Detection"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7932-4571","authenticated-orcid":false,"given":"Falih Gozi","family":"Febrinanto","sequence":"first","affiliation":[{"name":"Institute of Innovation, Science and Sustainability, Federation University Australia, Ballarat, Australia and CSIRO\u2019s Data61, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9962-5080","authenticated-orcid":false,"given":"Kristen","family":"Moore","sequence":"additional","affiliation":[{"name":"CSIRO\u2019s Data61, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3855-3378","authenticated-orcid":false,"given":"Chandra","family":"Thapa","sequence":"additional","affiliation":[{"name":"CSIRO\u2019s Data61, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0879-7168","authenticated-orcid":false,"given":"Mujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Innovation, Science and Sustainability, Federation\u00a0University Australia, Ballarat, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1010-0473","authenticated-orcid":false,"given":"Vidya","family":"Saikrishna","sequence":"additional","affiliation":[{"name":"Institute of Innovation, Science and Sustainability, Federation\u00a0University Australia, Ballarat, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8449-7610","authenticated-orcid":false,"given":"Jiangang","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Innovation, Science and Sustainability, Federation University Australia, Ballarat, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8324-1859","authenticated-orcid":false,"given":"Feng","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computing Technologies, RMIT University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"ACM SIGKDD","author":"Abdulaal Ahmed","year":"2021","unstructured":"Ahmed Abdulaal, Zhuanghua Liu, and Tomer Lancewicki. 2021. Practical approach to asynchronous multivariate time series anomaly detection and localization. In ACM SIGKDD."},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1145\/3055366.3055375","volume-title":"CySWater","author":"Ahmed Chuadhry Mujeeb","year":"2017","unstructured":"Chuadhry Mujeeb Ahmed, Venkata Reddy Palleti, and Aditya P. Mathur. 2017. WADI: A water distribution testbed for research in the design of secure cyber physical systems. In CySWater, 25\u201328."},{"key":"e_1_3_2_4_2","article-title":"Fast outlier detection in high dimensional spaces","author":"Angiulli Fabrizio","year":"2002","unstructured":"Fabrizio Angiulli and Clara Pizzuti. 2002. Fast outlier detection in high dimensional spaces. In ECML.","journal-title":"ECML"},{"key":"e_1_3_2_5_2","article-title":"Usad: Unsupervised anomaly detection on multivariate time series","author":"Audibert Julien","year":"2020","unstructured":"Julien Audibert, Pietro Michiardi, Fr\u00e9d\u00e9ric Guyard, S\u00e9bastien Marti, and Maria A. Zuluaga. 2020. Usad: Unsupervised anomaly detection on multivariate time series. In ACM SIGKDD.","journal-title":"ACM SIGKDD"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2019.100265"},{"issue":"3","key":"e_1_3_2_7_2","article-title":"VUS: Effective and efficient accuracy measures for time-series anomaly detection","volume":"34","author":"Boniol Paul","year":"2025","unstructured":"Paul Boniol, Ashwin K. Krishna, Marine Bruel, Qinghua Liu, Mingyi Huang, Themis Palpanas, Ruey S. Tsay, Aaron Elmore, Michael J. Franklin, and John Paparrizos. 2025. VUS: Effective and efficient accuracy measures for time-series anomaly detection. The VLDB Journal 34, 3 (2025), 32.","journal-title":"The VLDB Journal"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3638534"},{"key":"e_1_3_2_9_2","article-title":"Deep variational graph convolutional recurrent network for multivariate time series anomaly detection","author":"Chen Wenchao","year":"2022","unstructured":"Wenchao Chen, Long Tian, Bo Chen, Liang Dai, Zhibin Duan, and Mingyuan Zhou. 2022. Deep variational graph convolutional recurrent network for multivariate time series anomaly detection. In ICML.","journal-title":"ICML"},{"key":"e_1_3_2_10_2","article-title":"Balanced spatial-temporal graph structure","author":"Chen Weijun","year":"2023","unstructured":"Weijun Chen, Yanze Wang, Chengshuo Du, Zhenglong Jia, Feng Liu, and Ran Chen. 2023. Balanced spatial-temporal graph structure learning for multivariate time series forecasting: A trade-off between efficiency and flexibility. In ACML.","journal-title":"ACML"},{"key":"e_1_3_2_11_2","volume-title":"WSDM","author":"Chen Xuanhao","year":"2023","unstructured":"Xuanhao Chen, Liwei Deng, Yan Zhao, and Kai Zheng. 2023. Adversarial autoencoder for unsupervised time series anomaly detection and interpretation. In WSDM."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3100509"},{"key":"e_1_3_2_13_2","article-title":"CUTS+: high-dimensional causal discovery from irregular time-series","author":"Cheng Yuxiao","year":"2024","unstructured":"Yuxiao Cheng, Lianglong Li, Tingxiong Xiao, Zongren Li, Jinli Suo, Kunlun He, and Qionghai Dai. 2024. CUTS+: high-dimensional causal discovery from irregular time-series. In AAAI.","journal-title":"AAAI"},{"key":"e_1_3_2_14_2","volume-title":"ICML","author":"Dauphin Yann N.","year":"2017","unstructured":"Yann N. Dauphin, Angela Fan, Michael Auli, and David Grangier. 2017. Language modeling with gated convolutional networks. In ICML."},{"key":"e_1_3_2_15_2","article-title":"Graph neural network-based anomaly detection in multivariate time series","author":"Deng Ailin","year":"2021","unstructured":"Ailin Deng and Bryan Hooi. 2021. Graph neural network-based anomaly detection in multivariate time series. In AAAI.","journal-title":"AAAI"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2021.9010081"},{"key":"e_1_3_2_17_2","volume-title":"WSDM","author":"Febrinanto Falih Gozi","year":"2023","unstructured":"Falih Gozi Febrinanto. 2023. Efficient graph learning for anomaly detection systems. In WSDM."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2022.3222049"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105827"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.2307\/1912791"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2023.24830"},{"key":"e_1_3_2_22_2","first-page":"6990","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"8","author":"Ho Thi Kieu Khanh","year":"2025","unstructured":"Thi Kieu Khanh Ho, Ali Karami, and Narges Armanfard. 2025. Graph anomaly detection in time series: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 47, 8 (2025), 6990\u20137009."},{"key":"e_1_3_2_23_2","volume-title":"ACM SIGKDD","author":"Hundman Kyle","year":"2018","unstructured":"Kyle Hundman, Valentino Constantinou, Christopher Laporte, Ian Colwell, and Tom Soderstrom. 2018. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding. In ACM SIGKDD."},{"key":"e_1_3_2_24_2","volume-title":"SoutheastCon","author":"Ikegwu Kelechi M.","year":"2020","unstructured":"Kelechi M. Ikegwu, Jacob Trauger, Jeff McMullin, and Robert J. Brunner. 2020. PyIF: A fast and light weight implementation to estimate bivariate transfer entropy for big data. In SoutheastCon. IEEE."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2022.101672"},{"key":"e_1_3_2_26_2","volume-title":"ICLR","author":"Jang Eric","year":"2017","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical reparametrization with Gumble-Softmax. In ICLR."},{"issue":"9","key":"e_1_3_2_27_2","doi-asserted-by":"crossref","first-page":"6347","DOI":"10.1109\/TII.2020.2989810","article-title":"Quality-related root cause diagnosis based on orthogonal kernel principal component regression and transfer entropy","volume":"17","author":"Jiao Jianfang","year":"2020","unstructured":"Jianfang Jiao, Weiting Zhen, Wenxiang Zhu, and Guang Wang. 2020. Quality-related root cause diagnosis based on orthogonal kernel principal component regression and transfer entropy. IEEE Transactions on Industrial Informatics 17, 9 (2020), 6347\u20136356.","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"e_1_3_2_28_2","first-page":"10466","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"46","author":"Jin Ming","year":"2024","unstructured":"Ming Jin, Huan Yee Koh, Qingsong Wen, Daniele Zambon, Cesare Alippi, Geoffrey I. Webb, Irwin King, and Shirui Pan. 2024. A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 46, 12 (2024), 10466\u201310485."},{"key":"e_1_3_2_29_2","volume-title":"AAAI","author":"Kim Siwon","year":"2022","unstructured":"Siwon Kim, Kukjin Choi, Hyun-Soo Choi, Byunghan Lee, and Sungroh Yoon. 2022. Towards a rigorous evaluation of time-series anomaly detection. In AAAI."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.066138"},{"key":"e_1_3_2_31_2","volume-title":"ICANN","author":"Li Dan","year":"2019","unstructured":"Dan Li, Dacheng Chen, Baihong Jin, Lei Shi, Jonathan Goh, and See-Kiong Ng. 2019. MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks. In ICANN."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106919"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3711122"},{"key":"e_1_3_2_34_2","volume-title":"NeurIPS","author":"Li Zhixun","year":"2023","unstructured":"Zhixun Li, Xin Sun, Yifan Luo, Yanqiao Zhu, Dingshuo Chen, Yingtao Luo, Xiangxin Zhou, Qiang Liu, Shu Wu, Liang Wang, and Jeffrey Yu. 2023. GSLB: The graph structure learning benchmark. In NeurIPS."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671451"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2019.04.005"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"e_1_3_2_38_2","first-page":"109659","article-title":"Explainable artificial intelligence: Causal discovery and reasoning for geotechnical risk analysis","author":"Liu Wenli","year":"2023","unstructured":"Wenli Liu, Fenghua Liu, Weili Fang, and Peter E. D. Love. 2023. Explainable artificial intelligence: Causal discovery and reasoning for geotechnical risk analysis. Reliability Engineering & System Safety 241 (2023), 109659.","journal-title":"Reliability Engineering & System Safety"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CySWater.2016.7469060"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570906"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.85.461"},{"key":"e_1_3_2_42_2","volume-title":"ICLR","author":"Shang Chao","year":"2020","unstructured":"Chao Shang, Jie Chen, and Jinbo Bi. 2020. Discrete graph structure learning for forecasting multiple time series. In ICLR."},{"key":"e_1_3_2_43_2","first-page":"1759","volume-title":"ICDE","author":"Shen Siqi","year":"2025","unstructured":"Siqi Shen, Wentao Zhang, Chengshuo Du, Chong Chen, Fangcheng Fu, Yingxia Shao, and Bin Cui. 2025. Towards scalable and efficient graph structure learning. In ICDE. IEEE Computer Society, 1759\u20131772."},{"key":"e_1_3_2_44_2","volume-title":"ACM SIGKDD","author":"Siffer Alban","year":"2017","unstructured":"Alban Siffer, Pierre-Alain Fouque, Alexandre Termier, and Christine Largouet. 2017. Anomaly detection in streams with extreme value theory. In ACM SIGKDD."},{"key":"e_1_3_2_45_2","volume-title":"NeurIPS","author":"Song Junho","year":"2023","unstructured":"Junho Song, Keonwoo Kim, Jeonglyul Oh, and Sungzoon Cho. 2023. Memto: Memory-guided transformer for multivariate time series anomaly detection. In NeurIPS."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330672"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"issue":"8","key":"e_1_3_2_48_2","first-page":"4267","article-title":"Neural granger causality","volume":"44","author":"Tank Alex","year":"2021","unstructured":"Alex Tank, Ian Covert, Nicholas Foti, Ali Shojaie, and Emily B. Fox. 2021. Neural granger causality. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 8 (2021), 4267\u20134279.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.14778\/3514061.3514067"},{"key":"e_1_3_2_50_2","volume-title":"ICLR","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In ICLR."},{"key":"e_1_3_2_51_2","volume-title":"ICLR","author":"Welling Max","year":"2017","unstructured":"Max Welling and Thomas N. Kipf. 2017. Semi-supervised classification with graph convolutional networks. In ICLR."},{"issue":"34","key":"e_1_3_2_52_2","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.21105\/joss.01081","article-title":"IDTxl: The information dynamics toolkit xl: A python package for the efficient analysis of multivariate information dynamics in networks","volume":"4","author":"Wollstadt Patricia","year":"2019","unstructured":"Patricia Wollstadt, Joseph Lizier, Raul Vicente, Conor Finn, Mario Martinez-Zarzuela, Pedro Mediano, Leonardo Novelli, and Michael Wibral. 2019. IDTxl: The information dynamics toolkit xl: A python package for the efficient analysis of multivariate information dynamics in networks. Journal of Open Source Software 4, 34 (2019), 1081.","journal-title":"Journal of Open Source Software"},{"key":"e_1_3_2_53_2","volume-title":"ACM SIGKDD","author":"Wu Zonghan","year":"2020","unstructured":"Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Xiaojun Chang, and Chengqi Zhang. 2020. Connecting the dots: Multivariate time series forecasting with graph neural networks. In ACM SIGKDD."},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2023.3255590"},{"key":"e_1_3_2_55_2","unstructured":"Feng Xia Ciyuan Peng Jing Ren Falih Gozi Febrinanto Renqiang Luo Vidya Saikrishna Shuo Yu and Xiangjie Kong. 2025. Graph Learning. arXiv:2507.05636. Retrieved from https:\/\/arxiv.org\/abs\/2507.05636"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3076021"},{"key":"e_1_3_2_57_2","volume-title":"ICLR","author":"Yu Fisher","year":"2017","unstructured":"Fisher Yu and Vladlen Koltun. 2017. Multi-scale context aggregation by dilated convolutions. In ICLR."},{"issue":"2024","key":"e_1_3_2_58_2","first-page":"1","article-title":"Deep learning for time series anomaly detection: A survey","volume":"1","author":"Darban Zahra Zamanzadeh","year":"2024","unstructured":"Zahra Zamanzadeh Darban, Geoffrey I. Webb, Shirui Pan, Charu Aggarwal, and Mahsa Salehi. 2024. Deep learning for time series anomaly detection: A survey. ACM Computing Surveys (CSUR) 57, 1 (2024), 1\u201342.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00093"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3495161"},{"key":"e_1_3_2_61_2","volume-title":"ICLR","author":"Zong Bo","year":"2018","unstructured":"Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Daeki Cho, and Haifeng Chen. 2018. Deep autoencoding Gaussian mixture model for unsupervised anomaly detection. In ICLR."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T13:38:22Z","timestamp":1760708302000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":60,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3757922"],"URL":"https:\/\/doi.org\/10.1145\/3757922","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2023-12-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}