Trendshift - Ask AI

base on Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight), https://openreview.net/forum?id=JePfAI8fah # iTransformer The repo is the official implementation for the paper: [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://arxiv.org/abs/2310.06625). [[Slides]](https://cloud.tsinghua.edu.cn/f/175ff98f7e2d44fbbe8e/), [[Poster]](https://cloud.tsinghua.edu.cn/f/36a2ae6c132d44c0bd8c/). # Updates :triangular_flag_on_post: **News** (2024.10) [TimeXer](https://arxiv.org/abs/2402.19072), a canonical Transformer for forecasting with exogenous variables, is released. Code is available [here](https://github.com/thuml/TimeXer). :triangular_flag_on_post: **News** (2024.05) Many thanks for the great efforts from [lucidrains](https://github.com/lucidrains/iTransformer). A pip package for the usage of iTransformer variants can be simply installed via ```pip install iTransformer``` :triangular_flag_on_post: **News** (2024.04) iTransformer has benn included in [NeuralForecast](https://github.com/Nixtla/neuralforecast/blob/main/neuralforecast/models/itransformer.py). Special thanks to the contributor @[Marco](https://github.com/marcopeix)! :triangular_flag_on_post: **News** (2024.03) Introduction of our work in [Chinese](https://mp.weixin.qq.com/s/-pvBnA1_NSloNxa6TYXTSg) is available. :triangular_flag_on_post: **News** (2024.02) iTransformer has been accepted as **ICLR 2024 Spotlight**. :triangular_flag_on_post: **News** (2023.12) iTransformer available in [GluonTS](https://github.com/awslabs/gluonts/pull/3017) with probablistic head and support for static covariates. Notebook is available [here](https://github.com/awslabs/gluonts/blob/dev/examples/iTransformer.ipynb). :triangular_flag_on_post: **News** (2023.12) We received lots of valuable suggestions. A [revised version](https://arxiv.org/pdf/2310.06625v2.pdf) (**24 Pages**) is now available. :triangular_flag_on_post: **News** (2023.10) iTransformer has been included in [[Time-Series-Library]](https://github.com/thuml/Time-Series-Library) and achieves state-of-the-art in Lookback-$96$ forecasting. :triangular_flag_on_post: **News** (2023.10) All the scripts for the experiments in our [paper](https://arxiv.org/pdf/2310.06625.pdf) are available. ## Introduction 🌟 Considering the characteristics of multivariate time series, iTransformer breaks the conventional structure without modifying any Transformer modules. **Inverted Transformer is all you need in MTSF**. <img src="./figures/motivation.png" alt="" align=center /> 🏆 iTransformer achieves the comprehensive state-of-the-art in challenging multivariate forecasting tasks and solves several pain points of Transformer on extensive time series data. <img src="./figures/radar.png" height = "360" alt="" align=center /> ## Overall Architecture iTransformer regards **independent time series as variate tokens** to **capture multivariate correlations by attention** and **utilize layernorm and feed-forward networks to learn series representations**. <img src="./figures/architecture.png" alt="" align=center /> The pseudo-code of iTransformer is as simple as the following: <img src="./figures/algorithm.png" alt="" align=center /> ## Usage 1. Install Pytorch and necessary dependencies. ``` pip install -r requirements.txt ``` 1. The datasets can be obtained from [Google Drive](https://drive.google.com/file/d/1l51QsKvQPcqILT3DwfjCgx8Dsg2rpjot/view?usp=drive_link) or [Baidu Cloud](https://pan.baidu.com/s/11AWXg1Z6UwjHzmto4hesAA?pwd=9qjr). 2. Train and evaluate the model. We provide all the above tasks under the folder ./scripts/. You can reproduce the results as the following examples: ``` # Multivariate forecasting with iTransformer bash ./scripts/multivariate_forecasting/Traffic/iTransformer.sh # Compare the performance of Transformer and iTransformer bash ./scripts/boost_performance/Weather/iTransformer.sh # Train the model with partial variates, and generalize on the unseen variates bash ./scripts/variate_generalization/ECL/iTransformer.sh # Test the performance on the enlarged lookback window bash ./scripts/increasing_lookback/Traffic/iTransformer.sh # Utilize FlashAttention for acceleration bash ./scripts/efficient_attentions/iFlashTransformer.sh ``` ## Main Result of Multivariate Forecasting We evaluate the iTransformer on challenging multivariate forecasting benchmarks (**generally hundreds of variates**). **Comprehensive good performance** (MSE/MAE $\downarrow$) is achieved. ### Online Transaction Load Prediction of Alipay Trading Platform (Avg Results) <img src="./figures/main_results_alipay.png" alt="" align=center /> ## General Performance Boosting on Transformers By introducing the proposed framework, Transformer and its variants achieve **significant performance improvement**, demonstrating the **generality of the iTransformer approach** and **benefiting from efficient attention mechanisms**. <img src="./figures/boosting.png" alt="" align=center /> ## Zero-Shot Generalization on Variates **Technically, iTransformer is able to forecast with arbitrary numbers of variables**. We train iTransformers on partial variates and forecast unseen variates with good generalizability. <img src="./figures/generability.png" alt="" align=center /> ## Model Analysis Benefiting from inverted Transformer modules: - (Left) Inverted Transformers learn **better time series representations** (more similar [CKA](https://github.com/jayroxis/CKA-similarity)) favored by forecasting. - (Right) The inverted self-attention module learns **interpretable multivariate correlations**. <img src="./figures/analysis.png" alt="" align=center /> ## Citation If you find this repo helpful, please cite our paper. ``` @article{liu2023itransformer, title={iTransformer: Inverted Transformers Are Effective for Time Series Forecasting}, author={Liu, Yong and Hu, Tengge and Zhang, Haoran and Wu, Haixu and Wang, Shiyu and Ma, Lintao and Long, Mingsheng}, journal={arXiv preprint arXiv:2310.06625}, year={2023} } ``` ## Acknowledgement We appreciate the following GitHub repos a lot for their valuable code and efforts. - Reformer (https://github.com/lucidrains/reformer-pytorch) - Informer (https://github.com/zhouhaoyi/Informer2020) - FlashAttention (https://github.com/shreyansh26/FlashAttention-PyTorch) - Autoformer (https://github.com/thuml/Autoformer) - Stationary (https://github.com/thuml/Nonstationary_Transformers) - Time-Series-Library (https://github.com/thuml/Time-Series-Library) - lucidrains (https://github.com/lucidrains/iTransformer) This work was also supported by Ant Group through the CCF-Ant Research Fund. ## Contact If you have any questions or want to use the code, feel free to contact: * Yong Liu ([email protected]) * Haoran Zhang ([email protected]) * Tengge Hu ([email protected]) ", Assign "at most 3 tags" to the expected json: {"id":"4675","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"

AI prompts

AI prompts