Towards foundation auto-encoders for time-series anomaly detection.
Resumen:
We investigate a novel approach to time-series modeling, inspired by the successes of large pretrained foundation models. We introduce FAE (Foundation Auto-Encoders), a foundation generative-AI model for anomaly detection in time-series data, based on Variational Auto-Encoders (VAEs). By foundation, we mean a model pretrained on massive amounts of time-series data which can learn complex temporal patterns useful for accurate modeling, forecasting, and detection of anomalies on previously unseen datasets. FAE leverages VAEs and Dilated Convolutional Neural Networks (DCNNs) to build a generic model for univariate time-series modeling, which could eventually perform properly in out-of-the-box, zero-shot anomaly detection applications. We introduce the main concepts of FAE, and present preliminary results in different multidimensional time-series datasets from various domains, including a real dataset from an operational mobile ISP, and the well known KDD 2021 Anomaly Detection dataset.
| 2024 | |
| Este trabajo ha sido financiado parcialmente por FWF Austrian Science Fund, Project I-6653 GRAPHS4SEC, the Austrian FFG ICT- of-the-Future project DynAISEC – Adaptive AI/ML for Dynamic Cybersecurity Systems – ID 887504 y por el Proyecto uruguayo CSIC con referencia CSIC-I+D-22520220100371UD Generalization and Domain Adaptation in Time-Series Anomaly Detection. | |
|
Time-Series Data Anomaly Detection VAE Foundation Models |
|
| Inglés | |
| Universidad de la República | |
| COLIBRI | |
|
https://kdd-milets.github.io/milets2024/#introduction
https://hdl.handle.net/20.500.12008/49872 |
|
| Acceso abierto | |
| Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) |
| _version_ | 1872864819077447680 |
|---|---|
| author | García González, Gastón |
| author2 | Casas, Pedro Martínez, Emilio Fernández, Alicia |
| author2_role | author author author |
| author_facet | García González, Gastón Casas, Pedro Martínez, Emilio Fernández, Alicia |
| author_role | author |
| bitstream.checksum.fl_str_mv | 6429389a7df7277b72b7924fdc7d47a9 a006180e3f5b2ad0b88185d14284c0e0 4c31eff8bced6691f515913e11e0469d 3b50ae24bd8bd076d49a70878a8a2d2c 63a3d07915866db86c06df9555dc44d5 |
| bitstream.checksumAlgorithm.fl_str_mv | MD5 MD5 MD5 MD5 MD5 |
| bitstream.url.fl_str_mv | http://localhost:8080/xmlui/bitstream/20.500.12008/49872/5/license.txt http://localhost:8080/xmlui/bitstream/20.500.12008/49872/2/license_url http://localhost:8080/xmlui/bitstream/20.500.12008/49872/3/license_text http://localhost:8080/xmlui/bitstream/20.500.12008/49872/4/license_rdf http://localhost:8080/xmlui/bitstream/20.500.12008/49872/1/GCMF24.pdf |
| collection | COLIBRI |
| dc.contributor.filiacion.none.fl_str_mv | García González Gastón, Universidad de la República (Uruguay). Facultad de Ingeniería. Casas Pedro, AIT Austrian Institute of Technology Martínez Emilio, Universidad de la República (Uruguay). Facultad de Ingeniería. Fernández Alicia, Universidad de la República (Uruguay). Facultad de Ingeniería. |
| dc.creator.none.fl_str_mv | García González, Gastón Casas, Pedro Martínez, Emilio Fernández, Alicia |
| dc.date.accessioned.none.fl_str_mv | 2025-05-02T14:42:56Z |
| dc.date.available.none.fl_str_mv | 2025-05-02T14:42:56Z |
| dc.date.issued.none.fl_str_mv | 2024 |
| dc.description.abstract.none.fl_txt_mv | We investigate a novel approach to time-series modeling, inspired by the successes of large pretrained foundation models. We introduce FAE (Foundation Auto-Encoders), a foundation generative-AI model for anomaly detection in time-series data, based on Variational Auto-Encoders (VAEs). By foundation, we mean a model pretrained on massive amounts of time-series data which can learn complex temporal patterns useful for accurate modeling, forecasting, and detection of anomalies on previously unseen datasets. FAE leverages VAEs and Dilated Convolutional Neural Networks (DCNNs) to build a generic model for univariate time-series modeling, which could eventually perform properly in out-of-the-box, zero-shot anomaly detection applications. We introduce the main concepts of FAE, and present preliminary results in different multidimensional time-series datasets from various domains, including a real dataset from an operational mobile ISP, and the well known KDD 2021 Anomaly Detection dataset. |
| dc.description.sponsorship.none.fl_txt_mv | Este trabajo ha sido financiado parcialmente por FWF Austrian Science Fund, Project I-6653 GRAPHS4SEC, the Austrian FFG ICT- of-the-Future project DynAISEC – Adaptive AI/ML for Dynamic Cybersecurity Systems – ID 887504 y por el Proyecto uruguayo CSIC con referencia CSIC-I+D-22520220100371UD Generalization and Domain Adaptation in Time-Series Anomaly Detection. |
| dc.format.extent.es.fl_str_mv | 9 p. |
| dc.format.mimetype.es.fl_str_mv | application/pdf |
| dc.identifier.citation.es.fl_str_mv | García González, G., Casas, P., Martínez, E. y otros. Towards foundation auto-encoders for time-series anomaly detection [en línea]. EN: The 10th Mining and Learning from Time Series Workshop : From Classical Methods to LLMs (MILETS 2024), Barcelona, Spain, Aug 25th 2024, pp. 1-9. |
| dc.identifier.uri.none.fl_str_mv | https://kdd-milets.github.io/milets2024/#introduction https://hdl.handle.net/20.500.12008/49872 |
| dc.language.iso.none.fl_str_mv | en eng |
| dc.publisher.es.fl_str_mv | MILETS |
| dc.relation.none.fl_str_mv | The 10th Mining and Learning from Time Series Workshop : From Classical Methods to LLMs (MILETS 2024), Aug 25th, 2024 - KDD 2024, Barcelona, Spain, pp. 1-9. |
| dc.rights.license.none.fl_str_mv | Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) |
| dc.rights.none.fl_str_mv | info:eu-repo/semantics/openAccess |
| dc.source.none.fl_str_mv | reponame:COLIBRI instname:Universidad de la República instacron:Universidad de la República |
| dc.subject.es.fl_str_mv | Time-Series Data Anomaly Detection VAE Foundation Models |
| dc.title.none.fl_str_mv | Towards foundation auto-encoders for time-series anomaly detection. |
| dc.type.es.fl_str_mv | Ponencia |
| dc.type.none.fl_str_mv | info:eu-repo/semantics/conferenceObject |
| dc.type.version.none.fl_str_mv | info:eu-repo/semantics/publishedVersion |
| description | We investigate a novel approach to time-series modeling, inspired by the successes of large pretrained foundation models. We introduce FAE (Foundation Auto-Encoders), a foundation generative-AI model for anomaly detection in time-series data, based on Variational Auto-Encoders (VAEs). By foundation, we mean a model pretrained on massive amounts of time-series data which can learn complex temporal patterns useful for accurate modeling, forecasting, and detection of anomalies on previously unseen datasets. FAE leverages VAEs and Dilated Convolutional Neural Networks (DCNNs) to build a generic model for univariate time-series modeling, which could eventually perform properly in out-of-the-box, zero-shot anomaly detection applications. We introduce the main concepts of FAE, and present preliminary results in different multidimensional time-series datasets from various domains, including a real dataset from an operational mobile ISP, and the well known KDD 2021 Anomaly Detection dataset. |
| eu_rights_str_mv | openAccess |
| format | conferenceObject |
| id | COLIBRI_d92e6ef22eec7eece5a074d2c5f6ffdc |
| identifier_str_mv | García González, G., Casas, P., Martínez, E. y otros. Towards foundation auto-encoders for time-series anomaly detection [en línea]. EN: The 10th Mining and Learning from Time Series Workshop : From Classical Methods to LLMs (MILETS 2024), Barcelona, Spain, Aug 25th 2024, pp. 1-9. |
| instacron_str | Universidad de la República |
| institution | Universidad de la República |
| instname_str | Universidad de la República |
| language | eng |
| language_invalid_str_mv | en |
| network_acronym_str | COLIBRI |
| network_name_str | COLIBRI |
| oai_identifier_str | oai:colibri.udelar.edu.uy:20.500.12008/49872 |
| publishDate | 2024 |
| reponame_str | COLIBRI |
| repository.mail.fl_str_mv | karina.camps@seciu.edu.uy |
| repository.name.fl_str_mv | COLIBRI - Universidad de la República |
| repository_id_str | 4771 |
| rights_invalid_str_mv | Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) |
| spelling | García González Gastón, Universidad de la República (Uruguay). Facultad de Ingeniería.Casas Pedro, AIT Austrian Institute of TechnologyMartínez Emilio, Universidad de la República (Uruguay). Facultad de Ingeniería.Fernández Alicia, Universidad de la República (Uruguay). Facultad de Ingeniería.2025-05-02T14:42:56Z2025-05-02T14:42:56Z2024García González, G., Casas, P., Martínez, E. y otros. Towards foundation auto-encoders for time-series anomaly detection [en línea]. EN: The 10th Mining and Learning from Time Series Workshop : From Classical Methods to LLMs (MILETS 2024), Barcelona, Spain, Aug 25th 2024, pp. 1-9.https://kdd-milets.github.io/milets2024/#introductionhttps://hdl.handle.net/20.500.12008/49872We investigate a novel approach to time-series modeling, inspired by the successes of large pretrained foundation models. We introduce FAE (Foundation Auto-Encoders), a foundation generative-AI model for anomaly detection in time-series data, based on Variational Auto-Encoders (VAEs). By foundation, we mean a model pretrained on massive amounts of time-series data which can learn complex temporal patterns useful for accurate modeling, forecasting, and detection of anomalies on previously unseen datasets. FAE leverages VAEs and Dilated Convolutional Neural Networks (DCNNs) to build a generic model for univariate time-series modeling, which could eventually perform properly in out-of-the-box, zero-shot anomaly detection applications. We introduce the main concepts of FAE, and present preliminary results in different multidimensional time-series datasets from various domains, including a real dataset from an operational mobile ISP, and the well known KDD 2021 Anomaly Detection dataset.Submitted by Ribeiro Jorge (jribeiro@fing.edu.uy) on 2025-04-30T21:42:10Z No. of bitstreams: 2 license_rdf: 26539 bytes, checksum: 3b50ae24bd8bd076d49a70878a8a2d2c (MD5) GCMF24.pdf: 2982267 bytes, checksum: 63a3d07915866db86c06df9555dc44d5 (MD5)Approved for entry into archive by Machado Jimena (jmachado@fing.edu.uy) on 2025-05-02T13:55:21Z (GMT) No. of bitstreams: 2 license_rdf: 26539 bytes, checksum: 3b50ae24bd8bd076d49a70878a8a2d2c (MD5) GCMF24.pdf: 2982267 bytes, checksum: 63a3d07915866db86c06df9555dc44d5 (MD5)Made available in DSpace by Luna Fabiana (fabiana.luna@seciu.edu.uy) on 2025-05-02T14:42:56Z (GMT). No. of bitstreams: 2 license_rdf: 26539 bytes, checksum: 3b50ae24bd8bd076d49a70878a8a2d2c (MD5) GCMF24.pdf: 2982267 bytes, checksum: 63a3d07915866db86c06df9555dc44d5 (MD5) Previous issue date: 2024Este trabajo ha sido financiado parcialmente por FWF Austrian Science Fund, Project I-6653 GRAPHS4SEC, the Austrian FFG ICT- of-the-Future project DynAISEC – Adaptive AI/ML for Dynamic Cybersecurity Systems – ID 887504 y por el Proyecto uruguayo CSIC con referencia CSIC-I+D-22520220100371UD Generalization and Domain Adaptation in Time-Series Anomaly Detection.9 p.application/pdfenengMILETSThe 10th Mining and Learning from Time Series Workshop : From Classical Methods to LLMs (MILETS 2024), Aug 25th, 2024 - KDD 2024, Barcelona, Spain, pp. 1-9.Las obras depositadas en el Repositorio se rigen por la Ordenanza de los Derechos de la Propiedad Intelectual de la Universidad de la República.(Res. Nº 91 de C.D.C. de 8/III/1994 – D.O. 7/IV/1994) y por la Ordenanza del Repositorio Abierto de la Universidad de la República (Res. Nº 16 de C.D.C. de 07/10/2014)info:eu-repo/semantics/openAccessLicencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0)Time-Series DataAnomaly DetectionVAEFoundation ModelsTowards foundation auto-encoders for time-series anomaly detection.Ponenciainfo:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionreponame:COLIBRIinstname:Universidad de la Repúblicainstacron:Universidad de la RepúblicaGarcía González, GastónCasas, PedroMartínez, EmilioFernández, AliciaProcesamiento de SeñalesTratamiento de ImagenesLICENSElicense.txtlicense.txttext/plain; charset=utf-84267http://localhost:8080/xmlui/bitstream/20.500.12008/49872/5/license.txt6429389a7df7277b72b7924fdc7d47a9MD55CC-LICENSElicense_urllicense_urltext/plain; charset=utf-850http://localhost:8080/xmlui/bitstream/20.500.12008/49872/2/license_urla006180e3f5b2ad0b88185d14284c0e0MD52license_textlicense_texttext/html; charset=utf-829593http://localhost:8080/xmlui/bitstream/20.500.12008/49872/3/license_text4c31eff8bced6691f515913e11e0469dMD53license_rdflicense_rdfapplication/rdf+xml; charset=utf-826539http://localhost:8080/xmlui/bitstream/20.500.12008/49872/4/license_rdf3b50ae24bd8bd076d49a70878a8a2d2cMD54ORIGINALGCMF24.pdfGCMF24.pdfapplication/pdf2982267http://localhost:8080/xmlui/bitstream/20.500.12008/49872/1/GCMF24.pdf63a3d07915866db86c06df9555dc44d5MD5120.500.12008/498722025-05-02 11:42:56.972oai:colibri.udelar.edu.uy:20.500.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Institucionalhttps://www.colibri.udelar.edu.uyUniversidad públicahttps://udelar.edu.uy/https://www.colibri.udelar.edu.uy/oai/requestkarina.camps@seciu.edu.uyUruguayopendoar:47712025-05-02T14:42:56COLIBRI - Universidad de la Repúblicafalse |
| spellingShingle | Towards foundation auto-encoders for time-series anomaly detection. García González, Gastón Time-Series Data Anomaly Detection VAE Foundation Models |
| status_str | publishedVersion |
| title | Towards foundation auto-encoders for time-series anomaly detection. |
| title_full | Towards foundation auto-encoders for time-series anomaly detection. |
| title_fullStr | Towards foundation auto-encoders for time-series anomaly detection. |
| title_full_unstemmed | Towards foundation auto-encoders for time-series anomaly detection. |
| title_short | Towards foundation auto-encoders for time-series anomaly detection. |
| title_sort | Towards foundation auto-encoders for time-series anomaly detection. |
| topic | Time-Series Data Anomaly Detection VAE Foundation Models |
| url | https://kdd-milets.github.io/milets2024/#introduction https://hdl.handle.net/20.500.12008/49872 |
