# Decomposition-based multi-scale transformer framework for time series anomaly detection

arXiv: https://arxiv.org/abs/2504.14206 · HTML: https://mlsanity.com/paper/2504.14206/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 56 references that are in the map.
- First posted on arXiv 19 Apr 2025.

## Builds on (most cited first, 17 of 17)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https://mlsanity.com/paper/2201.07284/) (2022)
- [Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT](https://mlsanity.com/paper/2104.03466/) (2021)
- [DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detection](https://mlsanity.com/paper/2306.10347/) (2023)
- [Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding](https://mlsanity.com/paper/2011.14097/) (2020)
- [TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis](https://mlsanity.com/paper/2210.09693/) (2022)
- [Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives](https://mlsanity.com/paper/2201.11736/) (2022)
- [LSTM-Autoencoder based Anomaly Detection for Indoor Air Quality Time Series Data](https://mlsanity.com/paper/2204.06701/) (2022)
- [RoSAS: Deep Semi-Supervised Anomaly Detection with Contamination-Resilient Continuous Supervision](https://mlsanity.com/paper/2307.13239/) (2023)

## Built on by (most cited first, 5 of 5)

- [Multilingual Source Tracing of Speech Deepfakes: A First Benchmark](https://mlsanity.com/paper/2508.04143/) (2025)
- [Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternative](https://mlsanity.com/paper/2508.09294/) (2025)
- [Artificial Intelligence-Based Multiscale Temporal Modeling for Anomaly Detection in Cloud Services](https://mlsanity.com/paper/2508.14503/) (2025)
- [Pi-transformer: A prior-informed dual-attention model for multivariate time-series anomaly detection](https://mlsanity.com/paper/2509.19985/) (2025)
- [Fourier-KAN-Mamba: A Novel State-Space Equation Approach for Time-Series Anomaly Detection](https://mlsanity.com/paper/2511.15083/) (2025)

## Abstract (arXiv)

Time series anomaly detection is crucial for maintaining stable systems. Existing methods face two main challenges. First, it is difficult to directly model the dependencies of diverse and complex patterns within the sequences. Second, many methods that optimize parameters using mean squared error struggle with noise in the time series, leading to performance deterioration. To address these challenges, we propose a transformer-based framework built on decomposition (TransDe) for multivariate time series anomaly detection. The key idea is to combine the strengths of time series decomposition and transformers to effectively learn the complex patterns in normal time series data. A multi-scale patch-based transformer architecture is proposed to exploit the representative dependencies of each decomposed component of the time series. Furthermore, a contrastive learn paradigm based on patch operation is proposed, which leverages KL divergence to align the positive pairs, namely the pure representations of normal patterns between different patch-level views. A novel asynchronous loss function with a stop-gradient strategy is further introduced to enhance the performance of TransDe effectively. It can avoid time-consuming and labor-intensive computation costs in the optimization process. Extensive experiments on five public datasets are conducted and TransDe shows superiority compared with twelve baselines in terms of F1 score. Our code is available at https://github.com/shaieesss/TransDe.