Contextual Outlier Interpretation

Liu, Ninghao; Shin, DongHwa; Hu, Xia

doi:10.24963/ijcai.2018/341

Cited by 43 publications

(37 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two major interpretations of this outlier explanation. Some algorithms [47,86] interpret it as the smallest subspace where the outlier score is greater than a threshold (Definition 5), while others [61,68,90] interpret it as the subset of attributes where each member has a contribution score higher than a threshold (Definition 6).…”

Section: Outlying Attributes Of An Individual Outliermentioning

confidence: 99%

A survey on outlier explanations

et al. 2022

View full text Add to dashboard Cite

While many techniques for outlier detection have been proposed in the literature, the interpretation of detected outliers is often left to users. As a result, it is difficult for users to promptly take appropriate actions concerning the detected outliers. To lessen this difficulty, when outliers are identified, they should be presented together with their explanations. There are survey papers on outlier detection, but none exists for outlier explanations. To fill this gap, in this paper, we present a survey on outlier explanations in which meaningful knowledge is mined from anomalous data to explain them. We define different types of outlier explanations and discuss the challenges in generating each type. We review the existing outlier explanation techniques and discuss how they address the challenges. We also discuss the applications of outlier explanations and review the existing methods used to evaluate outlier explanations. Furthermore, we discuss possible future research directions.

show abstract

Section: Outlying Attributes Of An Individual Outliermentioning

confidence: 99%

A survey on outlier explanations

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In [ 71 ], the authors exploit the context of features within a training instance to improve explanations generated with LIME. In [ 72 ], the context of an instance that is being explained is generated for the purpose of up-sampling and generating explanations. A more advanced approach was discussed in [ 73 ], where an interactive explanation architecture was presented that allows for interactive verification and ad-hoc personalization of the explanations.…”

Section: Overview Of Semantic Data Mining Approachesmentioning

confidence: 99%

Semantic Data Mining in Ubiquitous Sensing: A Survey

Nalepa

Bobek

Kutt

et al. 2021

Sensors

View full text Add to dashboard Cite

Mining ubiquitous sensing data is important but also challenging, due to many factors, such as heterogeneous large-scale data that is often at various levels of abstraction. This also relates particularly to the important aspects of the explainability and interpretability of the applied models and their results, and thus ultimately to the outcome of the data mining process. With this, in general, the inclusion of domain knowledge leading towards semantic data mining approaches is an emerging and important research direction. This article aims to survey relevant works in these areas, focusing on semantic data mining approaches and methods, but also on selected applications of ubiquitous sensing in some of the most prominent current application areas. Here, we consider in particular: (1) environmental sensing; (2) ubiquitous sensing in industrial applications of artificial intelligence; and (3) social sensing relating to human interactions and the respective individual and collective behaviors. We discuss these in detail and conclude with a summary of this emerging field of research. In addition, we provide an outlook on future directions for semantic data mining in ubiquitous sensing contexts.

show abstract

“…In the context of high-dimensional data, interpretability is often addressed via dimensionality reductions such that every outlier can be described by a small subset of the original dimensions, see [39], [40]. Similarly, rate-distortion outliers can be characterized by their low-entropy representation: They are observations that make the representation unnecessarily complicated.…”

Section: How Can Rate-distortion Outliers Be Interpreted?mentioning

confidence: 99%

Cluster Purging: Efficient Outlier Detection based on Rate-Distortion Theory

Toller

Geiger

Kern

2021

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Rate-distortion theory-based outlier detection builds upon the rationale that a good data compression will encode outliers with unique symbols. Based on this rationale, we propose Cluster Purging, which is an extension of clustering-based outlier detection. This extension allows one to assess the representivity of clusterings, and to find data that are best represented by individual unique clusters. We propose two efficient algorithms for performing Cluster Purging, one being parameter-free, while the other algorithm has a parameter that controls representivity estimations, allowing it to be tuned in supervised setups. In an experimental evaluation, we show that Cluster Purging improves upon outliers detected from raw clusterings, and that Cluster Purging competes strongly against state-of-the-art alternatives.

show abstract

Contextual Outlier Interpretation

Cited by 43 publications

References 30 publications

A survey on outlier explanations

A survey on outlier explanations

Semantic Data Mining in Ubiquitous Sensing: A Survey

Cluster Purging: Efficient Outlier Detection based on Rate-Distortion Theory

Contact Info

Product

Resources

About