mlsanityData to 7 Oct 2026

TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data

arXiv 2201.07284 ↗First posted 18 Jan 2022cs.LGcited by 211

Not on the map. Why?

Abstract (arXiv)

Efficient anomaly detection and diagnosis in multivariate time-series data is of great importance for modern industrial applications. However, building a system that is able to quickly and accurately pinpoint anomalous observations is a challenging problem. This is due to the lack of anomaly labels, high data volatility and the demands of ultra-low inference times in modern applications. Despite the recent developments of deep learning approaches for anomaly detection, only a few of them can address all of these challenges. In this paper, we propose TranAD, a deep transformer network based anomaly detection and diagnosis model which uses attention-based sequence encoders to swiftly perform inference with the knowledge of the broader temporal trends in the data. TranAD uses focus score-based self-conditioning to enable robust multi-modal feature extraction and adversarial training to gain stability. Additionally, model-agnostic meta learning (MAML) allows us to train the model using limited data. Extensive empirical studies on six publicly available datasets demonstrate that TranAD can outperform state-of-the-art baseline methods in detection and diagnosis performance with data and time-efficient training. Specifically, TranAD increases F1 scores by up to 17%, reducing training times by up to 99% compared to the baselines.

Key facts. Cited by 211 papers in the map (data through 7 Oct 2026). Builds on 22 of its 71 references that are in the map. First posted on arXiv 18 Jan 2022.

Builds on

22 of 71 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2018Deep learning for time series classification: a reviewcited by 575
  6. 2019Federated Machine Learning: Concept and Applicationscited by 409
  7. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  8. 2019AutoML: A Survey of the State-of-the-Artcited by 388
  9. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  10. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  11. 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
  12. 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 181
10 more
  1. 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
  2. 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 165
  3. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 148
  4. 2020Exathlon: A Benchmark for Explainable Anomaly Detection over Time Seriescited by 56
  5. 2020Diverse Image Generation via Self-Conditioned GANscited by 54
  6. 2021Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signalscited by 41
  7. 2021COSCO: Container Orchestration using Co-Simulation and Gradient Based Optimization for Fog Computing Environmentscited by 19
  8. 2021PreGAN: Preemptive Migration Prediction Network for Proactive Fault-Tolerant Edge Computingcited by 8
  9. 2019Real-Time Sensor Anomaly Detection and Recovery in Connected Automated Vehicle Sensorscited by 7
  10. 2020Elle: Inferring Isolation Anomalies from Experimental Observationscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 15; 2023: 40; 2024: 42; 2025: 58; 2026: 56.

211 papers.

Sort:

By area:

  1. 2022Transformers in Time Series: A Surveycited by 489
  2. 2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 130
  3. 2022Deep Isolation Forest for Anomaly Detectioncited by 90
  4. 2022TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysiscited by 48
  5. 2024Can LLMs Understand Time Series Anomalies?cited by 41
  6. 2022Calibrated One-class Classification for Unsupervised Time Series Anomaly Detectioncited by 39
  7. 2023ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detectioncited by 38
  8. 2024TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Modelcited by 33
  9. 2024Graph Transformers: A Surveycited by 32
  10. 2024Large language models can be zero-shot anomaly detectors for time series?cited by 30
  11. 2024Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detectioncited by 26
  12. 2024Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detectioncited by 26
38 more
  1. 2023Navigating the Metric Maze: A Taxonomy of Evaluation Metrics for Anomaly Detection in Time Seriescited by 24
  2. 2023Weakly Supervised Anomaly Detection: A Surveycited by 22
  3. 2024TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Modelscited by 22
  4. 2022Detecting Multivariate Time Series Anomalies with Zero Known Labelcited by 21
  5. 2023Graph Anomaly Detection in Time Series: A Surveycited by 18
  6. 2023Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstructioncited by 17
  7. 2025Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Modelscited by 17
  8. 2023CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detectioncited by 15
  9. 2023Explainable Time Series Anomaly Detection using Masked Latent Generative Modelingcited by 15
  10. 2025Deep Learning Advancements in Anomaly Detection: A Comprehensive Surveycited by 15
  11. 2023Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsitycited by 14
  12. 2023Label-Free Multivariate Time Series Anomaly Detectioncited by 14
  13. 2025Positional Encoding in Transformer-Based Time Series Models: A Surveycited by 13
  14. 2023Unraveling the "Anomaly" in Time Series Anomaly Detection: A Self-supervised Tri-domain Solutioncited by 12
  15. 2024PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detectioncited by 12
  16. 2023Time Series Anomaly Detection using Diffusion-based Modelscited by 11
  17. 2024Multivariate Time-Series Anomaly Detection based on Enhancing Graph Attention Networks with Topological Analysiscited by 11
  18. 2023OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecastingcited by 10
  19. 2023Multi-scale Cross-restoration Framework for Electrocardiogram Anomaly Detectioncited by 10
  20. 2023A Systematic Review for Transformer-based Long-term Series Forecastingcited by 10
  21. 2024Sub-Adjacent Transformer: Improving Time Series Anomaly Detection with Reconstruction Error from Sub-Adjacent Neighborhoodscited by 10
  22. 2025FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detectioncited by 10
  23. 2022Is it worth it? Comparing six deep and classical methods for unsupervised anomaly detection in time seriescited by 9
  24. 2023DDMT: Denoising Diffusion Mask Transformer Models for Multivariate Time Series Anomaly Detectioncited by 9
  25. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  26. 2025Harnessing Vision-Language Models for Time Series Anomaly Detectioncited by 9
  27. 2025Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancycited by 9
  28. 2023Heterogeneous Anomaly Detection for Software Systems via Semi-supervised Cross-modal Attentioncited by 8
  29. 2023Sparse Binary Transformers for Multivariate Time Series Modelingcited by 8
  30. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  31. 2025DConAD: A Differencing-based Contrastive Representation Learning Framework for Time Series Anomaly Detectioncited by 7
  32. 2025Robust and Explainable Detector of Time Series Anomaly via Augmenting Multiclass Pseudo-Anomaliescited by 7
  33. 2022FedTADBench: Federated Time-Series Anomaly Detection Benchmarkcited by 6
  34. 2023Multivariate Time Series Anomaly Detection: Fancy Algorithms and Flawed Evaluation Methodologycited by 6
  35. 2023Twin Graph-based Anomaly Detection via Attentive Multi-Modal Learning for Microservice Systemcited by 6
  36. 2023TransNAS-TSAD: Harnessing Transformers for Multi-Objective Neural Architecture Search in Time Series Anomaly Detectioncited by 6
  37. 2023Entropy Causal Graphs for Multivariate Time Series Anomaly Detectioncited by 6
  38. 2024SimAD: A Simple Dissimilarity-based Approach for Time Series Anomaly Detectioncited by 6

50 most cited of 211 All 211 (JSON)