{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:31:27Z","timestamp":1792787487161,"version":"4.5.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"8","funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2024YFE0200800"],"award-info":[{"award-number":["2024YFE0200800"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62321001, 62471055, U23B2001, 62101064, 62171057, 62201072"],"award-info":[{"award-number":["62321001, 62471055, U23B2001, 62101064, 62171057, 62201072"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"High-Quality Development Project of the MIIT","award":["2440STCZB2584"],"award-info":[{"award-number":["2440STCZB2584"]}]},{"name":"Ministry of Education and China Mobile Joint Fund","award":["MCM20200202, MCM20180101"],"award-info":[{"award-number":["MCM20200202, MCM20180101"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2024PTB-004"],"award-info":[{"award-number":["2024PTB-004"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:p>\n                    Recently, reconstruction-based deep models have gained widespread usage in unsupervised anomaly detection. However, they may overlook some anomalies owing to the over-generalization of neural networks. Several studies have incorporated memory networks to mitigate this problem. Nonetheless, some of them lack an explicit memory updating process, while others rely on data-driven updating methods that are sensitive to initial values and unsuitable for end-to-end training. Additionally, the traditional criterion for detection computed in the high-dimensional input space may collapse as the spike in the deviation score is averaged across numerous dimensions. To address these challenges, we propose MCAKE, a\n                    <jats:italic toggle=\"yes\">M<\/jats:italic>\n                    emory-augmented\n                    <jats:italic toggle=\"yes\">C<\/jats:italic>\n                    ontrastive\n                    <jats:italic toggle=\"yes\">A<\/jats:italic>\n                    utoencoder with\n                    <jats:italic toggle=\"yes\">K<\/jats:italic>\n                    NN-Based\n                    <jats:italic toggle=\"yes\">E<\/jats:italic>\n                    xtraction. It is designed to highlight the deviation score for anomalies by reconstructing input using fixed normal prototypes recorded in the memory. We explicitly encourage the memory to be autonomously learned and effectively allocated through contrastive learning with multiple positive and multiple negative samples. Furthermore, we introduce a bivariate detection criterion that calculates anomaly scores considering both input and latent space to tackle the collapse. Extensive experiments on 50 datasets across various categories demonstrate the superiority of our approach, with a 2% relative improvement over the previous state-of-the-art models.\n                  <\/jats:p>","DOI":"10.1145\/3759460","type":"journal-article","created":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T20:41:46Z","timestamp":1755031306000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["MCAKE: Memory-Augmented Autoencoder with Contrastive Learning for Unsupervised Anomaly Detection"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3826-1148","authenticated-orcid":false,"given":"Chengsen","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of\u00a0Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0829-4624","authenticated-orcid":false,"given":"Qi","family":"Qi","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of\u00a0Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5830-6369","authenticated-orcid":false,"given":"Jinming","family":"Wu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of\u00a0Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3072-7422","authenticated-orcid":false,"given":"Haifeng","family":"Sun","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of\u00a0Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3345-1732","authenticated-orcid":false,"given":"Zirui","family":"Zhuang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of\u00a0Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7436-4784","authenticated-orcid":false,"given":"Yuhan","family":"Jing","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of\u00a0Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4404-3136","authenticated-orcid":false,"given":"Lianyuan","family":"Li","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2182-2228","authenticated-orcid":false,"given":"Jingyu","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Networking and Switching Technology, Beijing University of\u00a0Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In International Conference on Learning Representations, 1\u201315."},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1111\/coin.12156"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"e_1_3_1_5_2","first-page":"1597","volume-title":"International Conference on Machine Learning","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A simple framework for contrastive learning of visual representations\u00df. In International Conference on Machine Learning, 1597\u20131607."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450013"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16523"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669906"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3185059"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28682"},{"key":"e_1_3_1_11_2","first-page":"59","article-title":"Histogram-based outlier score (HBOS): A fast unsupervised anomaly detection algorithm","volume":"1","author":"Goldstein Markus","year":"2012","unstructured":"Markus Goldstein and Andreas Dengel. 2012. Histogram-based outlier score (HBOS): A fast unsupervised anomaly detection algorithm. German Conference on Artificial Intelligence 1 (2012), 59\u201363.","journal-title":"German Conference on Artificial Intelligence"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"e_1_3_1_14_2","first-page":"32142","article-title":"ADBench: Anomaly detection benchmark","author":"Han Songqiao","year":"2022","unstructured":"Songqiao Han, Xiyang Hu, Hailiang Huang, Minqi Jiang, and Yue Zhao. 2022. ADBench: Anomaly detection benchmark. In Neural Information Processing Systems, 32142\u201332159.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671943"},{"key":"e_1_3_1_16_2","first-page":"18661","article-title":"Supervised contrastive learning","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. In Neural Information Processing Systems, 18661\u201318673.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_1_17_2","first-page":"3469","volume-title":"International Conference on Learning Representations","author":"Kim Youngjin","year":"2018","unstructured":"Youngjin Kim, Minjung Kim, and Gunhee Kim. 2018. Memorization precedes generation: Learning unsupervised gans with memory networks. In International Conference on Learning Representations, 3469\u20133483."},{"key":"e_1_3_1_18_2","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2014","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-encoding variational bayes. In International Conference on Learning Representations, 1\u201314."},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3653677"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120612"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3332784"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00135"},{"key":"e_1_3_1_23_2","unstructured":"Zheng Li Yue Zhao Xiyang Hu Nicola Botta Cezar Ionescu and George H. Chen. 2022. 2022. ECOD: Unsupervised outlier detection using empirical cumulative distribution functions. arXiv:2201.00382. Retrieved from https:\/\/arxiv.org\/abs\/2201.00382"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/208"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"e_1_3_1_27_2","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. PyTorch: An imperative style, high-performance deep learning library. In Neural Information Processing Systems, 8024\u20138035.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335437"},{"key":"e_1_3_1_29_2","first-page":"1896","volume-title":"IEEE Winter Conference on Applications of Computer Vision","author":"Ravanbakhsh Mahdyar","year":"2019","unstructured":"Mahdyar Ravanbakhsh, Enver Sangineto, Moin Nabi, and Nicu Sebe. 2019. Training adversarial discriminators for cross-channel abnormal event detection in crowds. In IEEE Winter Conference on Applications of Computer Vision, 1896\u20131904."},{"key":"e_1_3_1_30_2","unstructured":"Adam Santoro Sergey Bartunov Matthew M. Botvinick Daan Wierstra and Timothy P. Lillicrap. 2016. One-shot learning with memory-augmented neural networks. arXiv:1605.06065. Retrieved from https:\/\/arxiv.org\/abs\/1605.06065"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1162\/089976601750264965"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_1_34_2","first-page":"6531","volume-title":"International Conference on Learning Representations","author":"Shenkar Tom","year":"2022","unstructured":"Tom Shenkar and Lior Wolf. 2022. Anomaly detection for tabular data with internal contrastive learning. In International Conference on Learning Representations, 6531\u20136556."},{"key":"e_1_3_1_35_2","first-page":"172","volume-title":"A Novel Anomaly Detection Scheme Based on Principal Component Classifier","author":"Shyu Meiling","year":"2003","unstructured":"Meiling Shyu, Shuching Chen, Kanoksri Sarinnapakorn, and Liwu Chang. 2003. A Novel Anomaly Detection Scheme Based on Principal Component Classifier. Technical Report. Miami Univ Coral Gables Fl Dept of Electrical and Computer Engineering, 172\u2013179."},{"key":"e_1_3_1_36_2","first-page":"57947","article-title":"MEMTO: Memory-guided transformer for multivariate time series anomaly detection","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 Neural Information Processing Systems, 57947\u201357963.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2007.70228"},{"key":"e_1_3_1_38_2","first-page":"2440","article-title":"End-to-end memory networks","author":"Sukhbaatar Sainbayar","year":"2015","unstructured":"Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, and Rob Fergus. 2015. End-to-end memory networks. In Neural Information Processing Systems, 2440\u20132448.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_1_39_2","first-page":"1511","volume-title":"International Joint Conference on Artificial Intelligence","author":"Tan Swee Chuan","year":"2011","unstructured":"Swee Chuan Tan, Kai Ming Ting, and Fei Tony Liu. 2011. Fast anomaly detection for streaming data. In International Joint Conference on Artificial Intelligence, 1511\u20131516."},{"key":"e_1_3_1_40_2","first-page":"10758","article-title":"Drift doesn\u2019t matter: Dynamic decomposition with diffusion reconstruction for unstable multivariate time series anomaly detection","author":"Wang Chengsen","year":"2023","unstructured":"Chengsen Wang, Zirui Zhuang, Qi Qi, Jingyu Wang, Xingyu Wang, Haifeng Sun, and Jianxin Liao. 2023. Drift doesn\u2019t matter: Dynamic decomposition with diffusion reconstruction for unstable multivariate time series anomaly detection. In Neural Information Processing Systems, 10758\u201310774.","journal-title":"Neural Information Processing Systems"},{"key":"e_1_3_1_41_2","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Weston Jason","year":"2015","unstructured":"Jason Weston, Sumit Chopra, and Antoine Bordes. 2015. Memory networks. In International Conference on Learning Representations, 1\u201315."},{"key":"e_1_3_1_42_2","first-page":"1","volume-title":"International Conference on Learning Representations","author":"Wu Haixu","year":"2023","unstructured":"Haixu Wu, Tengge Hu, Yong Liu, Hang Zhou, Jianmin Wang, and Mingsheng Long. 2023. TimesNet: Temporal 2D-variation modeling for general time series analysis. In International Conference on Learning Representations, 1\u201323."},{"key":"e_1_3_1_43_2","first-page":"1","article-title":"Deep isolation forest for anomaly detection","author":"Xu Hongzuo","year":"2023","unstructured":"Hongzuo Xu, Guansong Pang, Yijie Wang, and Yongjun Wang. 2023. Deep isolation forest for anomaly detection. IEEE Transactions on Knowledge and Data Engineering 35 (2023), 1\u201314.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33425"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3441448"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/332"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3572780"},{"key":"e_1_3_1_48_2","first-page":"3072","volume-title":"International Conference on Learning Representations","author":"Zong Bo","year":"2018","unstructured":"Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Dae-Ki Cho, and Haifeng Chen. 2018. Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In International Conference on Learning Representations, 3072\u20133090."}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3759460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:08:50Z","timestamp":1758301730000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3759460"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"references-count":47,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,9,30]]}},"alternative-id":["10.1145\/3759460"],"URL":"https:\/\/doi.org\/10.1145\/3759460","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"2024-10-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-02","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}