mlsanityData to 7 Oct 2026

CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching

arXiv 2410.12261 ↗First posted 16 Oct 2024cs.LG cs.AIcited by 91

Not on the map. Why?

Abstract (arXiv)

Anomaly detection in multivariate time series is challenging as heterogeneous subsequence anomalies may occur. Reconstruction-based methods, which focus on learning normal patterns in the frequency domain to detect diverse abnormal subsequences, achieve promising results, while still falling short on capturing fine-grained frequency characteristics and channel correlations. To contend with the limitations, we introduce CATCH, a framework based on frequency patching. We propose to patchify the frequency domain into frequency bands, which enhances its ability to capture fine-grained frequency characteristics. To perceive appropriate channel correlations, we propose a Channel Fusion Module (CFM), which features a patch-wise mask generator and a masked-attention mechanism. Driven by a bi-level multi-objective optimization algorithm, the CFM is encouraged to iteratively discover appropriate patch-wise channel correlations, and to cluster relevant channels while isolating adverse effects from irrelevant channels. Extensive experiments on 10 real-world datasets and 12 synthetic datasets demonstrate that CATCH achieves state-of-the-art performance. We make our code and datasets available at https://github.com/decisionintelligence/CATCH.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). Builds on 41 of its 103 references that are in the map. First posted on arXiv 16 Oct 2024.

Builds on

41 of 103 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  6. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  7. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  8. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
  9. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  10. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  11. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  12. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
29 more
  1. 2022How Do Vision Transformers Work?cited by 305
  2. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  3. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 242
  4. 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 165
  5. 2019Time-Series Anomaly Detection Service at Microsoftcited by 163
  6. 2022Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practicecited by 136
  7. 2024CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuningcited by 105
  8. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  9. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 103
  10. 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecastingcited by 102
  11. 2023The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecastingcited by 100
  12. 2022Local Evaluation of Time Series Anomaly Detection Algorithmscited by 79
  13. 2024FreDF: Learning to Forecast in the Frequency Domaincited by 77
  14. 2018Precision and Recall for Time Seriescited by 67
  15. 2024TSFM-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecastingcited by 55
  16. 2023LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Versioncited by 49
  17. 2023DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Predictioncited by 49
  18. 2022TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysiscited by 48
  19. 2024Fredformer: Frequency Debiased Transformer for Time Series Forecastingcited by 43
  20. 2021Unsupervised Path Representation Learning with Curriculum Negative Samplingcited by 42
  21. 2023ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyondcited by 39
  22. 2024Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoderscited by 37
  23. 2024Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfercited by 31
  24. 2024Hierarchical Classification Auxiliary Network for Time Series Forecastingcited by 26
  25. 2022Entire Space Counterfactual Learning for Reliable Content Recommendationscited by 13
  26. 2024Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspectivecited by 13
  27. 2024ICHPro: Intracerebral Hemorrhage Prognosis Classification Via Joint-attention Fusion-based 3d Cross-modal Networkcited by 10
  28. 2023SGDP: A Stream-Graph Neural Network Based Data Prefetchercited by 7
  29. 2024Interdependency Matters: Graph Alignment for Multivariate Time Series Anomaly Detectioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 39; 2026: 49.

91 papers.

Sort:

By area:

  1. 2025DBLoss: Decomposition-based Loss Function for Time Series Forecastingcited by 44
  2. 2025OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrievalcited by 40
  3. 2025Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspectivecited by 34
  4. 2025HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrievalcited by 32
  5. 2024EasyTime: Time Series Forecasting Made Easycited by 30
  6. 2025LightGTS: A Lightweight General Time Series Forecasting Modelcited by 28
  7. 2025Aurora: Towards Universal Generative Multimodal Time Series Forecastingcited by 28
  8. 2024Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systemscited by 25
  9. 2025Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecastingcited by 19
  10. 2024SSD-TS: Exploring the Potential of Linear State Space Models for Diffusion Models in Time Series Imputationcited by 18
  11. 2025CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentationcited by 12
  12. 2025CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modelingcited by 12
38 more
  1. 2026GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variablescited by 11
  2. 2025Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancycited by 9
  3. 2025MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Seriescited by 9
  4. 2025Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperationcited by 8
  5. 2025Selective Learning for Deep Time Series Forecastingcited by 8
  6. 2026Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecastingcited by 8
  7. 2025K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecastingcited by 7
  8. 2025ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecastingcited by 7
  9. 2025DDUNet: Dual Dynamic U-Net for Highly-Efficient Cloud Segmentationcited by 6
  10. 2025STAR: Boosting Time Series Foundation Models for Anomaly Detection through State-aware Adaptercited by 6
  11. 2025DeepFilter: A Transformer-style Framework for Accurate and Efficient Process Monitoringcited by 5
  12. 2025AimTS: Augmented Series and Image Contrastive Learning for Time Series Classificationcited by 5
  13. 2026PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detectioncited by 5
  14. 2025Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detectioncited by 4
  15. 2025CP2M: Clustered-Patch-Mixed Mosaic Augmentation for Aerial Image Segmentationcited by 3
  16. 2025FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecastingcited by 3
  17. 2026Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interactioncited by 3
  18. 2025Data Driven Decision Making with Time Series and Spatio-temporal Datacited by 2
  19. 2025Task-Aware Mixture-of-Experts for Time Series Analysiscited by 2
  20. 2025Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarkscited by 2
  21. 2026PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecastingcited by 2
  22. 2026Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarkingcited by 2
  23. 2026CANDI: Curated Test-Time Adaptation for Multivariate Time-Series Anomaly Detection Under Distribution Shiftcited by 2
  24. 2026Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariatecited by 2
  25. 2026WPBench: A Comprehensive Benchmark for Wind Power Forecastingcited by 2
  26. 2025Cluster-Aware Causal Mixer for Online Anomaly Detection in Multivariate Time Seriescited by 1
  27. 2025RATFM: Retrieval-augmented Time Series Foundation Model for Anomaly Detectioncited by 1
  28. 2025ADFormer: Aggregation Differential Transformer for Passenger Demand Forecastingcited by 1
  29. 2025Leveraging Intermediate Representations of Time Series Foundation Models for Anomaly Detectioncited by 1
  30. 2025Moon: A Modality Conversion-based Efficient Multivariate Time Series Anomaly Detectioncited by 1
  31. 2025RED-F: Reconstruction-Elimination based Dual-stream Contrastive Forecasting for Multivariate Time Series Anomaly Predictioncited by 1
  32. 2025SEED: Spectral Entropy-Guided Evaluation of SpatialTemporal Dependencies for Multivariate Time Series Forecastingcited by 1
  33. 2026SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacementcited by 1
  34. 2026ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologiescited by 1
  35. 2026Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offscited by 1
  36. 2026L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecastingcited by 1
  37. 2026Knowledge-Assisted Multi-Graph Dependency Learning for Multivariate Time Series Anomaly Detection in Multi-Stage Industrial Processescited by 1
  38. 2026GSLAD: Prototype-Regularized Graph Structure Learning for Multivariate Time Series Anomaly Detectioncited by 1

50 most cited of 91 All 91 (JSON)