Pre-trained KPI Anomaly Detection Model Through Disentangled Transformer-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Pre-trained KPI Anomaly Detection Model Through Disentangled Transformer

Published:2024-08-24 Issue: Volume:37 Page:6190-6201
ISSN:
Container-title:Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
language:
Short-container-title:

Author:

Yu Zhaoyang¹^ORCID,Pei Changhua²^ORCID,Wang Xin³^ORCID,Ma Minghua⁴^ORCID,Bansal Chetan⁴^ORCID,Rajmohan Saravan⁴^ORCID,Lin Qingwei⁵^ORCID,Zhang Dongmei⁵^ORCID,Wen Xidao⁶^ORCID,Li Jianhui²^ORCID,Xie Gaogang²^ORCID,Pei Dan¹^ORCID

Affiliation:

1. Tsinghua University & BNRist, Beijing, China

2. Computer Network Information Center, Chinese Academy of Sciences, Beijing, China

3. Stony Brook University, New York, USA

4. Microsoft, Redmond, USA

5. Microsoft, Beijing, China

6. BizSeer Technology, Beijing, China

Funder

National Key Research and Development Program of China

National Natural Science Foundation of China under Grant

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3637528.3671522

Reference42 articles.

1. Leo Breiman. 2001. Random forests. Machine learning, Vol. 45, 1 (2001), 5--32.

2. Holt-Winters forecasting: some practical issues;Chatfield Chris;Journal of the Royal Statistical Society: Series D (The Statistician),1988

3. Unsupervised Anomaly Detection for Intricate KPIs via Adversarial Training of VAE

4. Xuanhao Chen, Liwei Deng, Feiteng Huang, Chengwei Zhang, Zongquan Zhang, Yan Zhao, and Kai Zheng. 2021. DAEMON: Unsupervised Anomaly Detection and Interpretation for Multivariate Time Series. In ICDE. IEEE, 2225--2230.

5. Automatic Root Cause Analysis via Large Language Models for Cloud Incidents

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP