TimeMixer

kwuking/TimeMixer is ranked 9,134 among these 8 peers; albertpumarola/GANimation is ranked 9,141.

🌟 If you find this resource helpful, please consider to star this repository and cite our research: Updates 🚩 **News** (2024. 10): TimeMixer series has been included in **PyPOTS**. 10): We have newly released **TimeMixer++** as an upgraded version of TimeMixer. **TimeMixer++ is a time series pattern machine** that employs multi-scale and multi-resolution pattern extraction to **achieve 🏆state-of-the-art across 8 diverse analytical tasks! 07): TimeMixer has been included in **NeuralForecast**. Special thanks to the contributor @marcopeix and

@JQGoh! 07) TimeMixer has evolved into a **large model supporting comprehensive time series analysis, including long-term forecasting, short-term forecasting, anomaly detection, imputation, and classification**. In the future, we will further explore additional types of time series analysis tasks and strive to break through the limitations of current long-term forecasting to achieve efficient extreme-long-term time series forecasting. 06) **Introduction of TimeMixer** in **Chinese** is available. 05) TimeMixer has now released a **28-page full paper version

on arXiv**. Furthermore, we have provided a **brief video** to facilitate your understanding of our work. 05) TimeMixer currently **supports using future temporal features for prediction**. This feature has been well-received by the community members. You can now decide whether to enable this feature by using the parameter use_future_temporal_feature. 03) TimeMixer has been included in [[**Time-Series-Library**]]( and achieve the consistent 🏆**state-of-the-art** in **long-term time and short-term series forecasting** . 03

) TimeMixer has added a time-series decomposition method based on DFT, as well as downsampling operation based on 1D convolution. 02) TimeMixer has been accepted as **ICLR 2024 Poster**. Introduction 🏆 **TimeMixer**, as a fully MLP-based architecture, taking full advantage of disentangled multiscale time series, is proposed to **achieve consistent SOTA performances in both long and short-term forecasting tasks with favorable run-time efficiency**. 🌟**Observation 1: History Extraction** Given that seasonal and trend components exhibit significantly different characteristics in

time series, and different scales of the time series reflect different properties, with seasonal characteristics being more pronounced at a fine-grained micro-scale and trend characteristics being more pronounced at a coarse macro scale, it is, therefore, necessary to decouple seasonal and trend components at different scales. 🌟**Observation 2: Future Prediction** Different scales exhibit complementary predictive capabilities when integrating forecasts from different scales to obtain the final prediction results. Overall Architecture TimeMixer as a fully MLP-based architecture with

**Past-Decomposable-Mixing (PDM)** and **Future-Multipredictor-Mixing (FMM)** blocks to take full advantage of disentangled multiscale series in both past extraction and future prediction phases. Past Decomposable Mixing we propose the **Past-Decomposable-Mixing (PDM)** block to mix the decomposed seasonal and trend components in multiple scales separately. Empowered by seasonal and trend mixing, PDM progressively aggregates the detailed seasonal information from fine to coarse and dive into the macroscopic trend information with prior knowledge from coarser scales, eventually

achieving the multiscale mixing in past information extraction. Future Multipredictor Mixing Note that **Future Multipredictor Mixing (FMM)** is an ensemble