Anomaly Detection with Robust Deep Autoencoders

By Chong Zhou, Randy Clinton Paffenroth. Knowledge Discovery and Data Mining, 2017

1,548 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Civil and Structural Engineering

View Paper: https://www.semanticscholar.org/paper/2b75ba7f75170b73d913c515cc0deefef6c88f5f

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 Civil and Structural Engineering

Citations in the corpus

A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU (2023, neutral): “unsupervised learning tasks, such as generative modeling [54], dimensionality reduction [55], feature extraction [56], anomaly or outlier detection [57], and denoising [58].”
Student-Teacher Feature Pyramid Matching for Anomaly Detection (2021, background): “The main weakness of these approaches comes from the excellent generalization ability of the deep models, including variational autoencoder [3], robust autoencoder [47], conditional GAN [2], and bi-directional GAN [46], which probably allows anomalous images to be faithfully reconstructed.”
Adversarially Learned Anomaly Detection (2018, methodology): “Approaches based on autoencoders [20] and variational auto-encoders [21] first train a model to reconstruct normal data and subsequently identify anomalies as samples with high reconstruction errors.”
A Comprehensive Survey on Graph Anomaly Detection With Deep Learning (2021, background): “com/GuansongPang/deviation-network RDA [132] Python Tensorflow Static Graph https://github.”
Generative Adversarial Active Learning for Unsupervised Outlier Detection (2018, methodology): “, PCA [15], [29], Matrix Factorization (MF) [30], [31] and deep Auto-encoders [16], [32], map the instances to the output through the compression and decompression, and identify points with high reconstruction error as outliers.”
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].”
Anomaly Detection using One-Class Neural Networks (2018, methodology): “) are anomalies, as formulated in 2017 KDD paper [41].”
Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection (2018, background): “In addition, multiple recent works propose to analyze the reconstruction error induced by deep autoencoders, and demonstrate promising results (Zhou & Paffenroth (2017); Zhai et al. (2016)).”
Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection (2019, background): “Some very recent works [43, 46, 48, 6] train deep autoencoders for anomaly detection.”
Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals (2021, background): “Others like Denoising AutoEncoders (DAEs) [22], Deep Belief Networks (DBNs) [39] and Robust Deep Autoencoder (RDA) [40] have also been reported good performance for anomaly detection.”
Progress in Outlier Detection Techniques: A Survey (2019, background): “Using deep learning for unsupervised outlier detection problems has shown to be effective [211], [212].”
A Unifying Review of Deep and Shallow Anomaly Detection (2020, methodology): “AEs, for example, can be understood from an information-theoretic perspective [556] as adhering to the Infomax principle [557]–[559] by implicitly maximizing the mutual information between the input and latent code—subject to structural constraints or regularization of the code (e.g., “bottleneck,” ”
Deep Anomaly Detection with Deviation Networks (2019, methodology): “her, which poses significant challenges to widely-used optimization objectives that generally assume the data objects within each class are similar to each other. Existingdeepanomalydetection1 methods[2,7,19,20,22,29,30] address these two challenges by using unsupervised deep learning to model the n”
Deep Learning in Mobile and Wireless Networking: A Survey (2018, background): “For instance, deep AEs work well for unsupervised anomaly detection [463].”