MIX: A Joint Learning Framework for Detecting Both Clustered and Scattered Outliers in Mixed-Type Data

Xu, Hongzuo; Wang, Yijie; Wang, Yongjun; Wu, Zhang

doi:10.1109/icdm.2019.00182

Cited by 13 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This contradicts the findings of several other authors, see e.g. [11,24,2,3,7,12]. Furthermore, we saw from Figure 6 that in many cases, it is not, statistically, possible to assign a given sample to a single class.…”

Section: Discussioncontrasting

confidence: 92%

See 1 more Smart Citation

Detecting Outliers in High-dimensional Data with Mixed Variable Types using Conditional Gaussian Regression Models

Lindskou,

Tvedebrink,

Eriksen

et al. 2021

Preprint

View full text Add to dashboard Cite

Outlier detection has gained increasing interest in recent years, due to newly emerging technologies and the huge amount of high-dimensional data that are now available. Outlier detection can help practitioners to identify unwanted noise and/or locate interesting abnormal observations. To address this, we developed a novel method for outlier detection for use in, possibly high-dimensional, datasets with both discrete and continuous variables. We exploit the family of decomposable graphical models in order to model the relationship between the variables and use this to form an exact likelihood ratio test for an observation that is considered an outlier. We show that our method outperforms the state-of-the-art Isolation Forest algorithm on a real data example.

show abstract

Section: Discussioncontrasting

confidence: 92%

“…The problem is now reduced to inverting a (|pa j ∩ Γ|) × (|pa j ∩ Γ|) matrix. The qunatities Q h j can thus be computed using (24) twice; one with the new observation included and one without. Notice that the minimized sums of squared errors reduces as follows in the special cases:…”

Section: A Variance Estimation For Inhomogeneous Modelsmentioning

confidence: 99%

Detecting Outliers in High-dimensional Data with Mixed Variable Types using Conditional Gaussian Regression Models

Lindskou,

Tvedebrink,

Eriksen

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This contradicts the findings of several other authors, see e.g. Eiras-Franco et al ( 2019), Xu et al (2019), Aryal et al (2016Aryal et al ( , 2019, Domingues et al (2018), Emmott et al (2015). Furthermore, we saw from Figure 6 that in many cases, it is not, statistically, possible to assign a given sample to a single class.…”

Section: Discussioncontrasting

confidence: 97%

“…Hence, the information content of the data may be altered by the transformation, but nonetheless iForest is used in many papers on outlier detection with mixed data, and the performance is most often excellent, see e.g. Eiras-Franco et al ( 2019), Xu et al (2019), Aryal et al (2016), Garchery and Granitzer (2018) and Aryal et al (2019). In the review papers by Domingues et al (2018) and Emmott et al (2015), iForest is recommended as the best overall outlier detection procedure and is recommended in production environments.…”

Section: Introductionmentioning

confidence: 99%

Decomposable Graphical Models With a View Towards Outlier Detection and Sparse Tables

Lindskou¹

View full text Add to dashboard Cite

General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.-Users may download and print one copy of any publication from the public portal for the purpose of private study or research. -You may not further distribute the material or use it for any profit-making activity or commercial gain -You may freely distribute the URL identifying the publication in the public portal -

show abstract

“…How to handle categorical data has been a challenging problem. Most of the notions like distance metrics, density, or projection that are popularly used in numerical space cannot directly applied in categorical space [22]. Although one-hot encoding can transform categorical features into numerical data, the dimensionality of the transformed data increases to a large extent, and the transformed data is considerably sparse.…”

Section: Categorical Featuresmentioning

confidence: 99%

DRAM Failure Prediction in AIOps: Empirical Evaluation, Challenges and Opportunities

Wu,

Xu,

Pang

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

DRAM failure prediction is a vital task in AIOps, which is crucial to maintain the reliability and sustainable service of large-scale data centers. However, limited work has been done on DRAM failure prediction mainly due to the lack of public available datasets. This paper presents a comprehensive empirical evaluation of diverse machine learning techniques for DRAM failure prediction using a large-scale multisource dataset, including more than three millions of records of kernel, address, and mcelog data, provided by Alibaba Cloud through PAKDD 2021 competition. Particularly, we first formulate the problem as a multiclass classification task and exhaustively evaluate seven popular/stateof-the-art classifiers on both the individual and multiple data sources. We then formulate the problem as an unsupervised anomaly detection task and evaluate three state-of-the-art anomaly detectors. Further, based on the empirical results and our experience of attending this competition, we discuss major challenges and present future research opportunities in this task.

show abstract

MIX: A Joint Learning Framework for Detecting Both Clustered and Scattered Outliers in Mixed-Type Data

Cited by 13 publications

References 28 publications

Detecting Outliers in High-dimensional Data with Mixed Variable Types using Conditional Gaussian Regression Models

Detecting Outliers in High-dimensional Data with Mixed Variable Types using Conditional Gaussian Regression Models

Decomposable Graphical Models With a View Towards Outlier Detection and Sparse Tables

DRAM Failure Prediction in AIOps: Empirical Evaluation, Challenges and Opportunities

Contact Info

Product

Resources

About