arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.05865cs.LGstat.ML
收藏

通过深度度量学习和端到端优化进行无监督异常检测

Unsupervised Anomaly Detection via Deep Metric Learning with End-to-End Optimization

Bilkent University(比尔肯特大学);DataBoss A.S.(DataBoss公司)

Selim F. Yilmaz, Suleyman S. Kozat

摘要:

我们研究了高维数据的无监督异常检测,并介绍了一个基于深度度量学习(DML)的框架。特别是,我们通过深度神经网络学习距离度量。通过这个度量,我们将数据投影到度量空间中,更好地将异常数据与正常数据分开,并减少高维数据的维数灾难的影响。我们提出了一种新的数据蒸馏方法,通过自我监督,以弥补传统的做法,假设所有的数据是正常的。我们还采用了硬挖掘技术,从DML文献。我们表明,这些组件提高了我们的模型的性能,并显着减少运行时间。通过对14个真实世界数据集的广泛实验,与最先进的无监督异常检测方法相比,我们的方法表现出显着的性能提升,例如,14个数据集的平均绝对改善率在4.44%和11.74%之间。此外,我们在Github上分享了我们的方法的源代码,以方便进一步的研究。

英文摘要:

We investigate unsupervised anomaly detection for high-dimensional data and introduce a deep metric learning (DML) based framework. In particular, we learn a distance metric through a deep neural network. Through this metric, we project the data into the metric space that better separates the anomalies from the normal data and reduces the effect of the curse of dimensionality for high-dimensional data. We present a novel data distillation method through self-supervision to remedy the conventional practice of assuming all data as normal. We also employ the hard mining technique from the DML literature. We show these components improve the performance of our model and significantly reduce the running time. Through an extensive set of experiments on the 14 real-world datasets, our method demonstrates significant performance gains compared to the state-of-the-art unsupervised anomaly detection methods, e.g., an absolute improvement between 4.44% and 11.74% on the average over the 14 datasets. Furthermore, we share the source code of our method on Github to facilitate further research.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑