{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unsupervised-anomaly-detection-via","title":"Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications","arxiv_id":"1802.03903","date":"2018-02-12","proceeding":null,"authors":["Haowen Xu","Wenxiao Chen","Nengwen Zhao","Zeyan Li","Jiahao Bu","Zhihan Li","Ying Liu","Youjian Zhao","Dan Pei","Yang Feng","Jie Chen","Zhaogang Wang","Honglin Qiao"],"abstract":"To ensure undisrupted business, large Internet companies need to closely\nmonitor various KPIs (e.g., Page Views, number of online users, and number of\norders) of its Web applications, to accurately detect anomalies and trigger\ntimely troubleshooting/mitigation. However, anomaly detection for these\nseasonal KPIs with various patterns and data quality has been a great\nchallenge, especially without labels. In this paper, we proposed Donut, an\nunsupervised anomaly detection algorithm based on VAE. Thanks to a few of our\nkey techniques, Donut greatly outperforms a state-of-arts supervised ensemble\napproach and a baseline VAE approach, and its best F-scores range from 0.75 to\n0.9 for the studied KPIs from a top global Internet company. We come up with a\nnovel KDE interpretation of reconstruction for Donut, making it the first\nVAE-based anomaly detection algorithm with solid theoretical explanation.","url_abs":"http://arxiv.org/abs/1802.03903v1","url_pdf":"http://arxiv.org/pdf/1802.03903v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"unsupervised-anomaly-detection-via","repo_url":"https://github.com/korepwx/donut","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"unsupervised-anomaly-detection-via","repo_url":"https://github.com/KDD-OpenSource/DeepADoTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"unsupervised-anomaly-detection-via","repo_url":"https://github.com/ee357-computer-network/FinancialCrisisAL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"unsupervised-anomaly-detection-via","repo_url":"https://github.com/jackyue1994/sub_adjacent_transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unsupervised-anomaly-detection-via","repo_url":"https://github.com/nakumgaurav/Anomaly-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"unsupervised-anomaly-detection-via","repo_url":"https://github.com/nakumgaurav/Anomaly-Detection_Varitaional-Autoencoders","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"unsupervised-anomaly-detection-via","repo_url":"https://github.com/regel/loudml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"unsupervised-anomaly-detection-via","repo_url":"https://github.com/sharmi1206/featal-ecg-anomaly-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"unsupervised-anomaly-detection-via","repo_url":"https://github.com/thuml/Anomaly-Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unsupervised-anomaly-detection-via","repo_url":"https://github.com/yunchispk/WPS_PAKDD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"unsupervised-anomaly-detection","task_name":"Unsupervised Anomaly Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.03903","atlas_url":"https://app.syntology.ai/?focus=1802.03903","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}