Outlier Detection Using Replicator Neural Networks

By Simon Hawkins, Hongxing He, Graham J. Williams, Rohan A. Baxter. International Conference on Data Warehousing and Knowledge Discovery, 2002

785 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/353b5ed7874b7134ee95021bce60b7ac0ee7e1ed

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 Statistics and Probability

Citations in the corpus

A Unifying Review of Deep and Shallow Anomaly Detection (2020, methodology): “They were originally introduced during the 1980s [376]–[379] primarily as methods to perform nonlinear dimensionality reduction [380], [381], yet they have also been studied early on for AD [351], [352].”
Safe Visual Navigation via Deep Learning and Novelty Detection (2017, background): “including acoustic signals [22], network server anomalies [33], data mining [14], document classification [21] and others.”
Neural Networks and Deep Learning (2018, neutral): “The use of autoencoders for outlier detection is explored in [64, 181, 564], and a survey on the use in clustering is provided in [8].”
Outlier Detection with Autoencoder Ensembles (2017, methodology): “Data set RandNet Hawkins [10] LOF [6] HiCS [9] Spectral [18]”
Outlier Detection with Kernel Density Functions (2007, background): “We deflne outlier as an observation that deviates so much from other observations to arouse suspicion that it was generated by a difierent mechanism [ 13 ].”
Neural Trojans (2017, methodology): “The autoencoder, a.k.a. the replicator neural network [8], is a neural network with the same number of input and output neurons and has a bottleneck structure.”
A comparative study of RNN for outlier detection in data mining (2002, methodology): “We have proposed replicator neural networks (RNNs) for outlier detection [8].”
Deep One-Class Classification (2018, methodology): “Current approaches to deep AD have shown promising results (Hawkins et al., 2002; Sakurada & Yairi, 2014; Xu et al., 2015; Erfani et al., 2016; Andrews et al., 2016; Chen et al., 2017), but none of these methods are trained by optimizing an AD based objective function and typically rely on reconstru”
Anomaly detection: A survey (2009, methodology): “Replicator Neural Networks have been used for one-class anomaly detection [Hawkins et al. 2002; Williams et al. 2002].”
Autoencoder with recurrent neural networks for video forgery detection (2017, methodology): “It is also worth noting that in the literature autoencoders have been already proposed for anomaly detection in order to solve a one class clas-siﬁcation problem [12], and have been applied in very different applications [13, 14].”
Knowledge graph refinement: A survey of approaches and evaluation methods (2016, methodology): “Likewise, there are anomaly detection methods that build on learning predictive models [34,83].”
Deep Learning for Anomaly Detection: A Survey (2019, neutral): “The New York City taxi passenger data stream Cui et al. [2016] 1 https://cs.fit.edu/ ~pkc/nasa/data/ 2 https://github.com/khundman/telemanom 3 http://conferences.inf.ed.ac.uk/EuroDW2018/papers/eurodw18-Maia.pdf 4 https://www.kaggle.com/peterkim95/multivariate-gaussian-anomaly-detection/ data 5 https”
A Comprehensive Survey of Data Mining-based Fraud Detection Research (2010, methodology): “Unsupervised approaches include Hawkins et al (2002) and Williams et al (2002) which advocate replicator neural networks to detect outliers.”
SSD: A Unified Framework for Self-Supervised Outlier Detection (2021, methodology): “For example, autoencoder (AE) (Hawkins et al., 2002) based outlier detectors have achieved success in applications such as intrusion detection (Mirsky et al., 2018), and fraud detection (Schreyer et al., 2017).”
Enhancing one-class support vector machines for unsupervised anomaly detection (2013, background): “Replicator Neural Networks (RNNs) [11] are a semi-supervised neural network based approach.”
Fake Twitter followers detection by denoising autoencoder (2017, methodology): “[17]introduces the outlier factor OF i as a measure of outlyingness of the i -th record.”
Deep Anomaly Detection with Deviation Networks (2019, methodology): “Autoencoder-based methods [2, 7, 30] use a bottleneck network architecture to learn a low-dimensional representation space, and then use the learned representations to define reconstruction errors as anomaly scores.”