mlsanityData to 7 Oct 2026

Detecting Anomalies within Time Series using Local Neural Transformations

arXiv 2202.03944 ↗First posted 8 Feb 2022cs.LG cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

We develop a new method to detect anomalies within time series, which is essential in many application domains, reaching from self-driving cars, finance, and marketing to medical diagnosis and epidemiology. The method is based on self-supervised deep learning that has played a key role in facilitating deep anomaly detection on images, where powerful image transformations are available. However, such transformations are widely unavailable for time series. Addressing this, we develop Local Neural Transformations(LNT), a method learning local transformations of time series from data. The method produces an anomaly score for each time step and thus can be used to detect anomalies within time series. We prove in a theoretical analysis that our novel training objective is more suitable for transformation learning than previous deep Anomaly detection(AD) methods. Our experiments demonstrate that LNT can find anomalies in speech segments from the LibriSpeech data set and better detect interruptions to cyber-physical systems than previous work. Visualization of the learned transformations gives insight into the type of transformations that LNT learns.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 24 of its 54 references that are in the map. First posted on arXiv 8 Feb 2022.

Builds on

24 of 54 references.

References · 24

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  3. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  4. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  5. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  6. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  7. 2019On Mutual Information Maximization for Representation Learningcited by 315
  8. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  9. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  10. 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 213
  11. 2020Classification-Based Anomaly Detection for General Datacited by 210
  12. 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
12 more
  1. 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 181
  2. 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
  3. 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 165
  4. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 148
  5. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  6. 2020TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networkscited by 55
  7. 2020Viewmaker Networks: Learning Views for Unsupervised Representation Learningcited by 48
  8. 2021Neural Contextual Anomaly Detection for Time Seriescited by 42
  9. 2016Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Modelcited by 33
  10. 2016Variational Inference for On-line Anomaly Detection in High-Dimensional Time Seriescited by 12
  11. 2021Contrastive Predictive Coding for Anomaly Detectioncited by 10
  12. 2017Structured Embedding Models for Grouped Datacited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5; 2024: 3; 2025: 3.

12 papers.

  1. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  2. 2022Latent Outlier Exposure for Anomaly Detection with Contaminated Datacited by 48
  3. 2023Deep Anomaly Detection under Labeling Budget Constraintscited by 9
  4. 2023Model Selection of Anomaly Detectors in the Absence of Labeled Validation Datacited by 8
  5. 2024Denoising-Aware Contrastive Learning for Noisy Time Seriescited by 5
  6. 2025A Review on Self-Supervised Learning for Time Series Anomaly Detection: Recent Advances and Open Challengescited by 4
  7. 2023Zero-Shot Anomaly Detection via Batch Normalizationcited by 1
  8. 2024Self-Supervised Spatial-Temporal Normality Learning for Time Series Anomaly Detectioncited by 1
  9. 2025NeuCoReClass AD: Redefining Self-Supervised Time Series Anomaly Detectioncited by 1
  10. 2023A Generic Machine Learning Framework for Fully-Unsupervised Anomaly Detection with Contaminated Datacited by 0
  11. 2024Deep self-supervised learning with visualisation for automatic gesture recognitioncited by 0
  12. 2025rETF-semiSL: Semi-Supervised Learning for Neural Collapse in Temporal Datacited by 0