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

By Shehroz S. Khan, Michael G. Madden. 2013

617 citations recorded by the source corpus.

Abstract 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.

Subfields: Artificial Intelligence, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

Citations in the corpus

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems (2019, background): “, 2013; Kliger and Fleishman, 2018), and significant results have been achieved by conventional methods in low-dimensional spaces (Pimentel et al., 2014; Khan and Madden, 2014).”
A systematic study of the class imbalance problem in convolutional neural networks (2017, background): “Khan and Madden [66] review oneclass approaches in machine learning and divide them into One-class Support Vector Machines (OSVM) and Non-OSVM methods that include decision trees, neural networks etc.”
Learning Cumulatively to Become More Knowledgeable (2016, neutral): “[22] demonstrated that SVDD and one-class SVM are comparable when the Gaussian kernel is applied.”
Adversarially Learned One-Class Classifier for Novelty Detection (2018, background): “Novelty detection can be portrayed in the context of one-class classification [30, 13, 18], which aims (a)”
A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluation (2023, background): “This implies that classifiers are not built to distinguish between classes, but to only identify the majority class[277].”
Learning from positive and unlabeled data: a survey (2018, background): “The goal of one-class classification is to learn a model that identifies examples from a certain class: the positive class, when only examples of that class are available [47].”
Social Media Text Classification under Negative Covariate Shift (2015, methodology): “Also, as pointed out by (Khan and Madden, 2010; 2014), one drawback of their methods is that they often require a large dataset and the methods become very inefficient in high dimensional feature spaces.”
Breaking the Closed World Assumption in Text Classification (2016, methodology): “It has been shown that the use of Gaussian kernel makes SVDD and One-class SVM equivalent, and the results reported in (Khan and Madden, 2014) demonstrate that SVDD and One-class SVM are comparable when the Gaussian kernel is applied.”
A Unifying Review of Deep and Shallow Anomaly Detection (2020, background): “O N E - C L A S S C L A S S I F I C AT I O N One-class classification [223], [224], [301]–[303], occasionally also called single-class classification [304], [305], adopts a discriminative approach to AD.”
HRN: A Holistic Approach to One Class Learning (2020, background): “Recent surveys of one-class classiﬁcation can be found in [8, 37].”
Latent-Class Hough Forests for 3D Object Detection and Pose Estimation (2014, methodology): “We refer the reader to [19] for an in-depth review of one-class classification techniques.”