Additive Explanations for Anomalies Detected from Multivariate Temporal Data

Author:

Giurgiu Ioana1,Schumann Anika1

Affiliation:

1. IBM Research - Zurich, Zurich, Switzerland

Publisher

ACM

Reference12 articles.

1. A. Shrikumar etal 2017a. Learning Important Features Through Propagating Activation Differences. In ICML. A. Shrikumar et al. 2017a. Learning Important Features Through Propagating Activation Differences. In ICML.

2. C. Zhang etal 2018a. A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data. In arXiv:1811.08055. C. Zhang et al. 2018a. A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data. In arXiv:1811.08055.

3. E. Gutflaish etal 2019 a. Temporal Anomaly Detection: Calibrating the Surprise. In AAAI. E. Gutflaish et al. 2019 a. Temporal Anomaly Detection: Calibrating the Surprise. In AAAI.

4. M. Sundararajan etal 2017b. Axiomatic Attribution for Deep Networks. In ICML. M. Sundararajan et al. 2017b. Axiomatic Attribution for Deep Networks. In ICML.

Cited by 17 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. An Approach to Detect and Classify Potentially Suspicious Activity from Real-Time Log Data using Anomaly Detection Methods;2024 3rd International Conference for Innovation in Technology (INOCON);2024-03-01

2. Enhance Reading Comprehension from EEG-Based Brain-Computer Interface;Lecture Notes in Computer Science;2023-11-27

3. A Survey on Explainable Anomaly Detection;ACM Transactions on Knowledge Discovery from Data;2023-09-06

4. An artificial neural network toward simulating the treatment of wastes in multiphase reactors by ozonation;Chemical Engineering Journal;2023-09

5. Generative Perturbation Analysis for Probabilistic Black-Box Anomaly Attribution;Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2023-08-04

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

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3