{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:59:26Z","timestamp":1783439966305,"version":"3.54.6"},"reference-count":93,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2047418"],"award-info":[{"award-number":["IIS-2047418"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2007719"],"award-info":[{"award-number":["IIS-2007719"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF LEAP Center"},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-SC0022331"],"award-info":[{"award-number":["DE-SC0022331"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IARPA WRIVA program"},{"name":"Hasso Plattner Research Center","award":["UCI"],"award-info":[{"award-number":["UCI"]}]},{"DOI":"10.13039\/100014989","name":"Chan Zuckerberg Initiative","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014989","id-type":"DOI","asserted-by":"publisher"}]},{"name":"gifts from Qualcomm and Disney"},{"name":"Carl-Zeiss Foundation"},{"name":"DFG","award":["KL 2698\/2-1"],"award-info":[{"award-number":["KL 2698\/2-1"]}]},{"name":"DFG","award":["KL 2698\/5-1"],"award-info":[{"award-number":["KL 2698\/5-1"]}]},{"name":"BMBF","award":["03-B0770E"],"award-info":[{"award-number":["03-B0770E"]}]},{"name":"BMBF","award":["01-S21010C"],"award-info":[{"award-number":["01-S21010C"]}]},{"name":"DFG research unit","award":["5359"],"award-info":[{"award-number":["5359"]}]},{"name":"DFG research unit","award":["BU 4042\/2-1"],"award-info":[{"award-number":["BU 4042\/2-1"]}]},{"name":"DFG research unit","award":["KL 2698\/6-1"],"award-info":[{"award-number":["KL 2698\/6-1"]}]},{"name":"DFG research unit","award":["KL 2698\/7-1"],"award-info":[{"award-number":["KL 2698\/7-1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3519543","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:31:11Z","timestamp":1734550271000},"page":"2170-2185","source":"Crossref","is-referenced-by-count":12,"title":["Self-Supervised Anomaly Detection With Neural Transformations"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3699-7976","authenticated-orcid":false,"given":"Chen","family":"Qiu","sequence":"first","affiliation":[{"name":"Bosch Center for AI, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6829-3725","authenticated-orcid":false,"given":"Marius","family":"Kloft","sequence":"additional","affiliation":[{"name":"Department of Computer Science at RPTU Kaiserslautern-Landau, Kaiserslautern, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7836-7839","authenticated-orcid":false,"given":"Stephan","family":"Mandt","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Statistics, University of California, Irvine, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3739-2203","authenticated-orcid":false,"given":"Maja","family":"Rudolph","sequence":"additional","affiliation":[{"name":"Bosch Center for AI, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00057"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5712"},{"key":"ref3","article-title":"Graph anomaly detection at group level: A topology pattern enhanced unsupervised approach","author":"Ai","year":"2023","journal-title":"arXiv:2308.01063"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_39"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-014-0365-y"},{"key":"ref6","article-title":"Learning representations by maximizing mutual information across views","author":"Bachman","year":"2019"},{"key":"ref7","article-title":"The UEA multivariate time series classification archive","author":"Bagnall","year":"2018"},{"key":"ref8","article-title":"Extreme classification via adversarial softmax approximation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bamler"},{"key":"ref9","article-title":"Classification-based anomaly detection for general data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bergman"},{"key":"ref10","article-title":"Deep nearest neighbor anomaly detection","author":"Bergman","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"ref12","first-page":"1204","article-title":"GraphNorm: A principled approach to accelerating graph neural network training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cai"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4757427","article-title":"Harnessing contrastive learning and neural transformation for time series anomaly detection","author":"Chen","year":"2024"},{"key":"ref14","article-title":"Time-series anomaly detection via contextual discriminative contrastive learning","author":"Chen","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref16","article-title":"Unsupervised detection of lesions in brain MRI using constrained adversarial auto-encoders","volume-title":"Proc. MIDL Conf. Book","author":"Chen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref18","first-page":"3","article-title":"Image anomaly detection with generative adversarial networks","volume-title":"Proc. Joint Eur. Conf. Mach. Learn. Knowl. Discov. Databases","author":"Deecke"},{"key":"ref19","first-page":"2546","article-title":"Transfer-based semantic anomaly detection","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Deecke"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2496141"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.03.028"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976236.13"},{"key":"ref24","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris"},{"key":"ref25","first-page":"9758","article-title":"Deep anomaly detection using geometric transformations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Golan"},{"key":"ref26","first-page":"3711","article-title":"DROCC: Deep robust one-class classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goyal"},{"key":"ref27","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Gutmann"},{"issue":"2","key":"ref28","first-page":"307","article-title":"Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics","volume":"130","author":"Gutmann","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref30","article-title":"Deep anomaly detection with outlier exposure","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref31","first-page":"15663","article-title":"Using self-supervised learning can improve model robustness and uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hendrycks"},{"key":"ref32","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm"},{"key":"ref33","first-page":"2731","article-title":"Population based augmentation: Efficient learning of augmentation policy schedules","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ho"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.296"},{"key":"ref35","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3335317"},{"key":"ref37","article-title":"RaPP: Novelty detection with reconstruction along projection pathway","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref39","first-page":"19882","article-title":"Deep anomaly detection under labeling budget constraints","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01114"},{"key":"ref41","first-page":"6665","article-title":"Fast autoaugment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lim"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/2.36"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref44","article-title":"Explainable deep one-class classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liznerski"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-22086-3"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"ref47","article-title":"LSTM-based encoder-decoder for multi-sensor anomaly detection","author":"Malhotra","year":"2016"},{"key":"ref48","first-page":"139","article-title":"One-class SVMs for document classification","volume":"20","author":"Manevitz","year":"2001","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref50","first-page":"2265","article-title":"Learning word embeddings efficiently with noise-contrastive estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mnih"},{"key":"ref51","article-title":"Tudataset: A collection of benchmark datasets for learning with graphs","volume-title":"Proc. Workshop Graph Representation Learn. Beyond","author":"Morris"},{"key":"ref52","article-title":"graph2vec: Learning distributed representations of graphs","author":"Narayanan","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-015-5517-9"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/app132111938"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref56","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref57","first-page":"1532","article-title":"Glove: Global vectors for word representation","volume-title":"Proc. Empirical Methods Natural Lang. Process.","author":"Pennington"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00301"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966273"},{"key":"ref60","first-page":"8703","article-title":"Neural transformation learning for deep anomaly detection beyond images","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qiu"},{"key":"ref61","first-page":"18153","article-title":"Latent outlier exposure for anomaly detection with contaminated data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qiu"},{"key":"ref62","first-page":"3239","article-title":"Learning to compose domain-specific transformations for data augmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ratner"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00283"},{"key":"ref64","first-page":"4393","article-title":"Deep one-class classification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ruff"},{"key":"ref65","article-title":"Deep semi-supervised anomaly detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ruff"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1398"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3052449"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00727-3"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"ref70","article-title":"Detecting anomalies within time series using local neural transformations","author":"Schneider","year":"2022"},{"key":"ref71","article-title":"SSD: A unified framework for self-supervised outlier detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sehwag"},{"key":"ref72","article-title":"Anomaly detection for tabular data with internal contrastive learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shenkar"},{"issue":"9","key":"ref73","first-page":"2539","article-title":"Weisfeiler-Lehman graph Kernels","volume":"120","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref74","article-title":"Learning and evaluating representations for deep one-class classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sohn"},{"key":"ref75","first-page":"11839","article-title":"CSI: Novelty detection via contrastive learning on distributionally shifted instances","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Tack"},{"key":"ref76","article-title":"Viewmaker networks: Learning views for unsupervised representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tamkin"},{"key":"ref77","first-page":"2794","article-title":"A Bayesian data augmentation approach for learning deep models","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Tran"},{"key":"ref78","article-title":"On mutual information maximization for representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tschannen"},{"key":"ref79","first-page":"87","article-title":"Hunt for the unique, stable, sparse and fast feature learning on graphs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Verma"},{"key":"ref80","first-page":"5060","article-title":"Multivariate triangular quantile maps for novelty detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977653.ch78"},{"key":"ref82","first-page":"5962","article-title":"Effective end-to-end unsupervised outlier detection via inlier priority of discriminative network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref83","article-title":"Learning perturbation sets for robust machine learning","author":"Wong","year":"2020"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2009.87"},{"key":"ref85","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref86","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref87","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref89","article-title":"Adversarial autoaugment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1089\/big.2021.0069"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098052"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.07.179"},{"key":"ref93","article-title":"Deep autoencoding Gaussian mixture model for unsupervised anomaly detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zong"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10873290\/10806806-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10806806.pdf?arnumber=10806806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:39:20Z","timestamp":1738867160000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10806806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":93,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3519543","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}