Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

169338506675 · Jun 202019922001200920172026
48 results for deep anomaly detection

Improves anomaly detection with contaminated unlabeled data.

problem Weakness in existing semi-supervised anomaly detection methods when unlabeled data contain anomalies.
method Integrates positive-unlabeled learning with deep anomaly detection models.
result Achieves better detection performance on various datasets.

Although deep learning has been applied to successfully address many data mining problems, relatively limited work has been done on deep learning for anomaly detection. Existing deep anomaly detection methods, which focus on learning new feature representations to enable downstream anomaly detection methods, perform in…

2019-11-19abs ↗pdf ↗

Survey evaluates 20 anomaly detection methods for time-series data.

problem Comparing statistical, machine learning, and deep learning methods for anomaly detection.
method Comprehensive evaluation of 20 methods from three categories on public datasets.
result Provides insights into the performance and suitability of anomaly detection methods.

Deep RL detects anomalies from few labeled examples and large unlabeled data.

problem Anomaly detection with limited labeled data and large unlabeled data.
method Deep reinforcement learning to optimize detection of labeled and unlabeled anomalies.
result Significantly outperforms state-of-the-art methods on 48 real-world datasets.

Research shows deep generative models' likelihoods are unreliable for anomaly detection.

problem Anomaly detection using deep generative models' likelihoods is unreliable.
method Examined the behavior of distribution densities through reparametrization.
result The likelihoods used for anomaly detection rely on strong and implicit hypotheses.

Deep approaches to anomaly detection have recently shown promising results over shallow methods on large and complex datasets. Typically anomaly detection is treated as an unsupervised learning problem. In practice however, one may have---in addition to a large set of unlabeled samples---access to a small pool of label…

2019-06-06abs ↗pdf ↗

FCDD explains deep anomaly detection by mapping anomalies away and providing heatmap explanations.

problem Deep one-class classification's non-linear transformation makes it hard to interpret.
method FCDD learns a mapping that concentrates nominal samples, maps anomalies away, and provides heatmap explanations.
result FCDD sets a new state of the art in unsupervised anomaly detection on MVTec-AD.

Anomalies are intuitively easy for human experts to understand, but they are hard to define mathematically. Therefore, in order to have performance guarantees in unsupervised anomaly detection, priors need to be assumed on what the anomalies are. By contrast, active learning provides the necessary priors through approp…

2018-05-23abs ↗pdf ↗

Deep semi-supervised anomaly detection improves fraud detection in financial markets.

problem Detecting fraud in high-frequency financial data with limited labeled examples.
method Evaluation of Deep Semi-Supervised Anomaly Detection (Deep SAD) on proprietary limit order book data.
result Deep SAD significantly improves fraud detection accuracy with minimal labeled data.

InQMAD detects anomalies in streaming data using quantum measurements and density matrices.

problem Detecting anomalies in streaming data with challenges like conceptual drift and continuous learning.
method Incremental anomaly detection based on random Fourier features and quantum measurements.
result InQMAD outperforms 12 state-of-the-art methods in a systematic evaluation.

Online anomaly detection in surveillance videos with false alarm rate bounds.

problem Lack of theoretical performance analysis and online decision making in anomaly detection.
method Proposes an online anomaly detection method with asymptotic bounds on false alarm rate.
result Demonstrates effectiveness on publicly available data sets, outperforming state-of-the-art algorithms.

Many deep models have been recently proposed for anomaly detection. This paper presents comparison of selected generative deep models and classical anomaly detection methods on an extensive number of non--image benchmark datasets. We provide statistical comparison of the selected models, in many configurations, archite…

2018-07-13abs ↗pdf ↗

Unsupervised deep learning detects and localizes crop leaf diseases.

problem Automated detection and localization of crop diseases.
method Three types of autoencoders (CAE, CVAE, VQ-VAE) applied to an open-source dataset.
result VQ-VAE autoencoder outperforms in image reconstruction, anomaly removal, detection, and localization.

Paper tackles anomaly detection in SAR images without labeled data.

problem Anomaly detection in SAR images with speckle noise and spatial correlation issues.
method Self-supervised deep learning approach: despeckling, adversarial autoencoder, change detection.
result Method outperforms conventional algorithms in detecting anomalies in SAR images.

Dividing deep learning models for consistent anomaly detection in changing log data.

problem Anomaly detection methods fail when log data types change, leading to false negatives.
method Divide deep learning models based on log data correlation and extract correlations.
result Continues anomaly detection accuracy even when log data changes.

This paper proposes a communication-efficient deep anomaly detection framework for industrial IoT.

problem Accurately detecting anomalies in time-series data from edge devices in industrial IoT.
method A federated learning-based approach with an Attention Mechanism-based Convolutional Neural Network-Long Short Term Memory (AMCNN-LSTM) model and gradient compression.
result The proposed framework accurately and timely detects anomalies with reduced communication overhead.

New method improves anomaly detection in acoustic signals.

problem Poor anomaly detection performance in existing acoustic signal-based unsupervised methods.
method Deep autoencoding Gaussian mixture model with hyper-parameter optimization.
result Significantly improved anomaly detection performance compared to previous methods.

Proposes a method to detect anomalies in multi-subgroup normal data.

problem Anomaly detection with limited labeled anomalies and multi-subgroup normal data.
method Learn multi-normal prototypes with deep embedding clustering and contrastive learning. Estimate the likelihood of unlabeled samples being normal during training.
result Superior performance compared to state-of-the-art methods on various datasets.

Recent semi-supervised anomaly detection methods that are trained using small labeled anomaly examples and large unlabeled data (mostly normal data) have shown largely improved performance over unsupervised methods. However, these methods often focus on fitting abnormalities illustrated by the given anomaly examples on…

2019-10-30abs ↗pdf ↗

ResGCN detects anomalies in attributed networks by capturing sparsity and nonlinearity.

problem Detecting anomalous nodes in attributed networks.
method Attention-based deep residual modeling using Graph Convolutional Networks.
result ResGCN effectively detects anomalies in attributed networks.

Proposes a new VAE framework for anomaly detection in time series data.

problem Data scarcity leads to latent holes and discontinuous regions in latent space, causing non-robust reconstructions.
method Combines VAEs with self-supervised learning to address data scarcity and improve anomaly detection.
result Improves robustness of anomaly detection in time series data by addressing latent holes and discontinuities.

It is important to detect anomalous inputs when deploying machine learning systems. The use of larger and more complex inputs in deep learning magnifies the difficulty of distinguishing between anomalous and in-distribution examples. At the same time, diverse image and text data are available in enormous quantities. We…

2018-12-11abs ↗pdf ↗

DPGIIL clusters structural anomalies using transmissibility functions with deep learning and Dirichlet process.

problem Clustering structural anomalies in high-dimensional streaming data with optimal cluster number determination.
method Combines Dirichlet process and deep generative models for incremental learning and anomaly detection.
result DPGIIL outperforms traditional methods in anomaly detection and clustering.

Deep AD on images outperforms traditional methods.

problem Traditional AD methods struggle with unsupervised learning due to lack of labeled data.
method Used deep learning on ImageNet to discern between normal and a few random natural images.
result Deep AD classifiers trained on a few random images outperform current state-of-the-art methods.

Meta-AAD uses deep reinforcement learning to improve anomaly detection by selecting the most informative instances.

problem High false-positive rate in anomaly detection, especially in high-stake applications.
method Meta-AAD leverages deep reinforcement learning to train a meta-policy for query selection, optimizing the number of discovered anomalies.
result Meta-AAD significantly outperforms state-of-the-art re-ranking strategies and unsupervised baselines on 24 benchmark datasets.

Survey on LSTM-based anomaly detection for technical systems.

problem Detect anomalies in technical systems due to complex dynamics.
method Use LSTM networks and other AI techniques to detect anomalies considering temporal and contextual characteristics.
result Demonstrates the potential of LSTM networks and graph-based approaches for anomaly detection.

The paper provides theoretical guarantees for neural network-based anomaly detection.

problem Theoretical guarantees for unsupervised neural network-based anomaly detection.
method Casting anomaly detection as a binary classification problem, establishing non-asymptotic upper bounds and convergence rates.
result The convergence rate on the excess risk matches the minimax optimal rate.