mlsanityData to 7 Oct 2026

Weakly Augmented Variational Autoencoder in Time Series Anomaly Detection

arXiv 2401.03341 ↗First posted 7 Jan 2024cs.LG stat.MLcited by 2

Not on the map. Why?

Abstract (arXiv)

Due to their unsupervised training and uncertainty estimation, deep Variational Autoencoders (VAEs) have become powerful tools for reconstruction-based Time Series Anomaly Detection (TSAD). Existing VAE-based TSAD methods, either statistical or deep, tune meta-priors to estimate the likelihood probability for effectively capturing spatiotemporal dependencies in the data. However, these methods confront the challenge of inherent data scarcity, which is often the case in anomaly detection tasks. Such scarcity easily leads to latent holes, discontinuous regions in latent space, resulting in non-robust reconstructions on these discontinuous spaces. We propose a novel generative framework that combines VAEs with self-supervised learning (SSL) to address this issue.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 7 Jan 2024.

Builds on

36 of 58 references.

References · 36

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  3. 2019Modeling Tabular data using Conditional GANcited by 695
  4. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  5. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
  6. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  7. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  8. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  9. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 233
  10. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 223
  11. 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 213
  12. 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
24 more
  1. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  2. 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 181
  3. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 143
  4. 2018Recent Advances in Autoencoder-Based Representation Learningcited by 130
  5. 2017InfoVAE: Information Maximizing Variational Autoencoderscited by 124
  6. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  7. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  8. 2023Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglementcited by 89
  9. 2023DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Modelscited by 81
  10. 2022SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantizationcited by 68
  11. 2023Bayesian Flow Networkscited by 62
  12. 2022Decoupling Local and Global Representations of Time Seriescited by 17
  13. 2023Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstructioncited by 17
  14. 2019Robust Variational Autoencoders for Outlier Detection and Repair of Mixed-Type Datacited by 16
  15. 2022Markovian Gaussian Process Variational Autoencoderscited by 16
  16. 2017Variational Inference based on Robust Divergencescited by 15
  17. 2023Tree Variational Autoencoderscited by 10
  18. 2023C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confoundercited by 7
  19. 2019Robust Variational Autoencodercited by 6
  20. 2023eVAE: Evolutionary Variational Autoencodercited by 6
  21. 2023Trading Information between Latents in Hierarchical Variational Autoencoderscited by 6
  22. 2019Coupled VAE: Improved Accuracy and Robustness of a Variational Autoencodercited by 5
  23. 2022Adversarial robustness of VAEs through the lens of local geometrycited by 4
  24. 2023C2VAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posteriorcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2024FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantificationcited by 4
  2. 2026Unsupervised Anomaly Detection in Process-Complex Industrial Time Series: A Real-World Case Studycited by 0