Research on Cost-Sensitive Learning in One-Class Anomaly Detection Algorithms

Luo, Jun; Pan, Zhisong; Ni, Guiqiang; Hu, Guyu

doi:10.1007/978-3-540-73547-2_27

Cited by 10 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Luo et al . (2007) extends the work of Tax and Duin (2001b) to propose a cost-sensitive OSVM algorithm called Frequency-Based SVDD (F-SVDD) and Write-Related SVDD (WS-SVDD) for intrusion detection problem. The SVDD method gives equal cost to classification errors, whereas F-SVDD gives higher cost to frequent short sequences occurring during system calls and WS-SVDD gives different costs to different system calls.…”

Section: Proposed Taxonomymentioning

confidence: 92%

“…Data-dependent approaches that deduce cost of errors from the training data objects may not generalize the cost across different domains of even same application area. In the papers we reviewed, only one research paper discusses the cost-sensitive aspect of OCC (Luo et al ., 2007) and it shows that this area of research is largely unexplored. We believe that approaches based on careful application of Preference Elicitation techniques (Chen & Pu, 2004) can be useful to deduce cost of errors.…”

Section: Conclusion and Open Research Questionsmentioning

confidence: 99%

See 1 more Smart Citation

One-class classification: taxonomy of study and review of techniques

Khan

Madden

2014

The Knowledge Engineering Review

458

252

View full text Add to dashboard Cite

One-class classification (OCC) algorithms aim to build classification models when the negative class is either absent, poorly sampled or not well defined. This unique situation constrains the learning of efficient classifiers by defining class boundary just with the knowledge of positive class. The OCC problem has been considered and applied under many research themes, such as outlier/ novelty detection and concept learning. In this paper, we present a unified view of the general problem of OCC by presenting a taxonomy of study for OCC problems, which is based on the availability of training data, algorithms used and the application domains applied. We further delve into each of the categories of the proposed taxonomy and present a comprehensive literature review of the OCC algorithms, techniques and methodologies with a focus on their significance, limitations and applications. We conclude our paper by discussing some open research problems in the field of OCC and present our vision for future research.

show abstract

Section: Proposed Taxonomymentioning

confidence: 92%

Section: Conclusion and Open Research Questionsmentioning

confidence: 99%

One-class classification: taxonomy of study and review of techniques

Khan

Madden

2014

The Knowledge Engineering Review

458

252

View full text Add to dashboard Cite

show abstract

“…Both (Yang and Madden, 2007) and (Tian and Gu, 2010) tried to refine Schölkopf's models by searching optimal parameters. Luo et al, (2007) proposed a cost-sensitive one-class SVM algorithm for intrusion detection. We will see in the experiment section that one-class classification is far inferior to our proposed CBS-L method.…”

Section: Related Workmentioning

confidence: 99%

Social Media Text Classification under Negative Covariate Shift

Fei¹,

Liu²

2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

In a typical social media content analysis task, the user is interested in analyzing posts of a particular topic. Identifying such posts is often formulated as a classification problem. However, this problem is challenging. One key issue is covariate shift. That is, the training data is not fully representative of the test data. We observed that the covariate shift mainly occurs in the negative data because topics discussed in social media are highly diverse and numerous, but the user-labeled negative training data may cover only a small number of topics. This paper proposes a novel technique to solve the problem. The key novelty of the technique is the transformation of document representation from the traditional ngram feature space to a center-based similarity (CBS) space. In the CBS space, the covariate shift problem is significantly mitigated, which enables us to build much better classifiers. Experiment results show that the proposed approach markedly improves classification.

show abstract

“…Whereas previous approaches to this problem used a cost function that is constant within the ball and grows linearly outside of it [3,30,33], the approach taken by [34] employs a cost function that grows linearly within the ball but is kept constant outside of it. Other papers employing the one-class SVM technique include [18,26]. Also relevant is the approach of [31] for estimating the support of a distribution -although in this paper, the existence of a kernel is assumed, which is a much stronger assumption than that of a metric.…”

Section: Related Workmentioning

confidence: 99%

Metric Anomaly Detection via Asymmetric Risk Minimization

Kontorovich

Hendler

Menahem

2011

Similarity-Based Pattern Recognition

View full text Add to dashboard Cite

Abstract.We propose what appears to be the first anomaly detection framework that learns from positive examples only and is sensitive to substantial differences in the presentation and penalization of normal vs. anomalous points. Our framework introduces a novel type of asymmetry between how false alarms (misclassifications of a normal instance as an anomaly) and missed anomalies (misclassifications of an anomaly as normal) are penalized: whereas each false alarm incurs a unit cost, our model assumes that a high global cost is incurred if one or more anomalies are missed. We define a few natural notions of risk along with efficient minimization algorithms. Our framework is applicable to any metric space with a finite doubling dimension. We make minimalistic assumptions that naturally generalize notions such as margin in Euclidean spaces. We provide a theoretical analysis of the risk and show that under mild conditions, our classifier is asymptotically consistent. The learning algorithms we propose are computationally and statistically efficient and admit a further tradeoff between running time and precision. Some experimental results on real-world data are provided.

show abstract

Research on Cost-Sensitive Learning in One-Class Anomaly Detection Algorithms

Cited by 10 publications

References 3 publications

One-class classification: taxonomy of study and review of techniques

One-class classification: taxonomy of study and review of techniques

Social Media Text Classification under Negative Covariate Shift

Metric Anomaly Detection via Asymmetric Risk Minimization

Contact Info

Product

Resources

About