thuml/Time-Series-Library thuml/Time-Series-Library

  • Stars
    star
    3,852
  • Rank 10,938 (Top 0.3 %)
  • Language
    Shell
  • License
    MIT License
  • Created over 1 year ago
  • Updated 3 months ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
thuml/Time-Series-Library
github

thuml

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

A Library for Advanced Deep Time Series Models.

Time Series Library (TSlib)

TSlib is an open-source library for deep learning researchers, especially deep time series analysis.

We provide a neat code base to evaluate advanced deep time series models or develop your own model, which covers five mainstream tasks: long- and short-term forecasting, imputation, anomaly detection, and classification.

Leaderboard for Time Series Analysis

Till February 2023, the top three models for five different tasks are:

Model
Ranking		 Long-term
Forecasting		 Short-term
Forecasting		 Imputation Anomaly
Detection		 Classification
πŸ₯‡ 1st TimesNet TimesNet TimesNet TimesNet TimesNet
πŸ₯ˆ 2nd DLinear Non-stationary
Transformer		 Non-stationary
Transformer		 Non-stationary
Transformer		 FEDformer
πŸ₯‰ 3rd Non-stationary
Transformer		 FEDformer Autoformer Informer Autoformer

Note: We will keep updating this leaderborad. If you have proposed advanced and awesome models, welcome to send your paper/code link to us or raise a pull request. We will add them to this repo and update the leaderborad as soon as possible.

Compared models of this leaderboard. β˜‘ means that their codes have already been included in this repo.

  • TimesNet - TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis [ICLR 2023] [Code]
  • DLinear - Are Transformers Effective for Time Series Forecasting? [AAAI 2023] [Code]
  • LightTS - Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures [arXiv 2022] [Code]
  • ETSformer - ETSformer: Exponential Smoothing Transformers for Time-series Forecasting [arXiv 2022] [Code]
  • Non-stationary Transformer - Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting [NeurIPS 2022] [Code]
  • FEDformer - FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting [ICML 2022] [Code]
  • Pyraformer - Pyraformer: Low-complexity Pyramidal Attention for Long-range Time Series Modeling and Forecasting [ICLR 2022] [Code]
  • Autoformer - Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting [NeurIPS 2021] [Code]
  • Informer - Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting [AAAI 2021] [Code]
  • Reformer - Reformer: The Efficient Transformer [ICLR 2020] [Code]
  • Transformer - Attention is All You Need [NeurIPS 2017] [Code]

See our latest paper [TimesNet] for the comprehensive benchmark. We will release a real-time updated online version soon.

Newly added baselines. We will add them into the leaderboard after a comprehensive evaluation.

  • FiLM - FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting [NeurIPS 2022][Code]
  • PatchTST - A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. [ICLR 2023] [Code]
  • MICN - MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting [ICLR 2023][Code]
  • Crossformer - Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting [ICLR 2023][Code]

Usage

  1. Install Python 3.8. For convenience, execute the following command.
pip install -r requirements.txt
  1. Prepare Data. You can obtained the well pre-processed datasets from [Google Drive], [Tsinghua Cloud] or [Baidu Drive]. Then place the downloaded data under the folder ./dataset. Here is a summary of supported datasets.

  1. Train and evaluate model. We provide the experiment scripts of all benchmarks under the folder ./scripts/. You can reproduce the experiment results as the following examples:
# long-term forecast
bash ./scripts/long_term_forecast/ETT_script/TimesNet_ETTh1.sh
# short-term forecast
bash ./scripts/short_term_forecast/TimesNet_M4.sh
# imputation
bash ./scripts/imputation/ETT_script/TimesNet_ETTh1.sh
# anomaly detection
bash ./scripts/anomaly_detection/PSM/TimesNet.sh
# classification
bash ./scripts/classification/TimesNet.sh
  1. Develop your own model.
  • Add the model file to the folder ./models. You can follow the ./models/Transformer.py.
  • Include the newly added model in the Exp_Basic.model_dict of ./exp/exp_basic.py.
  • Create the corresponding scripts under the folder ./scripts.

Citation

If you find this repo useful, please cite our paper.

@inproceedings{wu2023timesnet,
  title={TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis},
  author={Haixu Wu and Tengge Hu and Yong Liu and Hang Zhou and Jianmin Wang and Mingsheng Long},
  booktitle={International Conference on Learning Representations},
  year={2023},
}

Contact

If you have any questions or suggestions, feel free to contact:

or describe it in Issues.

Acknowledgement

This project is supported by the National Key R&D Program of China (2021YFB1715200).

This library is constructed based on the following repos:

All the experiment datasets are public and we obtain them from the following links:

More Repositories

1

Transfer-Learning-Library

Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
Python
3,189
star
2

Autoformer

About Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https://arxiv.org/abs/2106.13008
Jupyter Notebook
1,645
star
3

Anomaly-Transformer

About Code release for "Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy" (ICLR 2022 Spotlight), https://openreview.net/forum?id=LzQQ89U1qm_
Python
589
star
4

iTransformer

Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight), https://openreview.net/forum?id=JePfAI8fah
Python
569
star
5

TimesNet

About Code release for "TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis" (ICLR 2023), https://openreview.net/pdf?id=ju_Uqw384Oq
544
star
6

Xlearn

Transfer Learning Library
Jupyter Notebook
455
star
7

Nonstationary_Transformers

Code release for "Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting" (NeurIPS 2022), https://arxiv.org/abs/2205.14415
Python
405
star
8

predrnn-pytorch

Official implementation for NIPS'17 paper: PredRNN: Recurrent Neural Networks for Predictive Learning Using Spatiotemporal LSTMs.
Python
398
star
9

CDAN

Code release for "Conditional Adversarial Domain Adaptation" (NIPS 2018)
Jupyter Notebook
387
star
10

Flowformer

About Code release for "Flowformer: Linearizing Transformers with Conservation Flows" (ICML 2022), https://arxiv.org/pdf/2202.06258.pdf
Python
281
star
11

Universal-Domain-Adaptation

Code release for Universal Domain Adaptation(CVPR 2019)
Python
261
star
12

depyf

depyf is a tool to help you understand and adapt to PyTorch compiler torch.compile.
Python
254
star
13

HashNet

Code release for "HashNet: Deep Learning to Hash by Continuation" (ICCV 2017)
Jupyter Notebook
239
star
14

LogME

Code release for "LogME: Practical Assessment of Pre-trained Models for Transfer Learning" (ICML 2021) and Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs (JMLR 2022)
Python
194
star
15

A-Roadmap-for-Transfer-Learning

141
star
16

Koopa

Code release for "Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors" (NeurIPS 2023), https://arxiv.org/abs/2305.18803
Python
134
star
17

Corrformer

About code release of "Interpretable Weather Forecasting for Worldwide Stations with a Unified Deep Model", Nature Machine Intelligence, 2023. https://www.nature.com/articles/s42256-023-00667-9
Python
131
star
18

MDD

Code released for ICML 2019 paper "Bridging Theory and Algorithm for Domain Adaptation".
Python
125
star
19

Self-Tuning

Code release for "Self-Tuning for Data-Efficient Deep Learning" (ICML 2021)
Python
109
star
20

PADA

Code release for "Partial Adversarial Domain Adaptation" (ECCV 2018)
Python
97
star
21

Batch-Spectral-Penalization

Code release for Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation (ICML 2019)
Python
89
star
22

Transferable-Adversarial-Training

Code release for Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML2019)
Python
78
star
23

TransNorm

Code release for "Transferable Normalization: Towards Improving Transferability of Deep Neural Networks" (NeurIPS 2019)
Python
76
star
24

MTlearn

Code release for "Learning Multiple Tasks with Multilinear Relationship Networks" (NIPS 2017)
Python
70
star
25

HashGAN

HashGAN: Deep Learning to Hash with Pair Conditional Wasserstein GAN
Python
69
star
26

SAN

Code release for "Partial Transfer Learning with Selective Adversarial Networks" (CVPR 2018)
Jupyter Notebook
67
star
27

Domain-Adaptation-Regression

Code release for Representation Subspace Distance for Domain Adaptation Regression (ICML 2021)
Python
67
star
28

Deep-Embedded-Validation

Code release for Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation (ICML 2019)
Python
59
star
29

SimMTM

About Code release for "SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling" (NeurIPS 2023 Spotlight), https://arxiv.org/abs/2302.00861
Python
57
star
30

MADA

Code release for "Multi-Adversarial Domain Adaptation" (AAAI 2018)
C++
55
star
31

CLIPood

About Code Release for "CLIPood: Generalizing CLIP to Out-of-Distributions" (ICML 2023), https://arxiv.org/abs/2302.00864
Python
54
star
32

ETN

Code released for CVPR 2019 paper "Learning to Transfer Examples for Partial Domain Adaptation"
Python
49
star
33

Debiased-Self-Training

Code release of paper Debiased Self-Training for Semi-Supervised Learning (NeurIPS 2022 Oral)
49
star
34

Latent-Spectral-Models

About Code Release for "Solving High-Dimensional PDEs with Latent Spectral Models" (ICML 2023), https://arxiv.org/abs/2301.12664
Python
48
star
35

Versatile-Domain-Adaptation

Code Release for "Minimum Class Confusion for Versatile Domain Adaptation"(ECCV2020)
Python
48
star
36

Separate_to_Adapt

Code release for Separate to Adapt: Open Set Domain Adaptation via Progressive Separation (CVPR 2019)
Python
48
star
37

MotionRNN

About Code release for "MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying Motions" (CVPR 2021) https://arxiv.org/abs/2103.02243
Python
46
star
38

ContextWM

Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://arxiv.org/abs/2305.18499
Python
42
star
39

CoTuning

Code release for NeurIPS 2020 paper "Co-Tuning for Transfer Learning"
Python
38
star
40

AutoTimes

Official implementation for "AutoTimes: Autoregressive Time Series Forecasters via Large Language Models"
Python
33
star
41

Calibrated-Multiple-Uncertainties

Code Release for "Learning to Detect Open Classes for Universal Domain Adaptation"(ECCV2020)
Python
29
star
42

OpenDG-DAML

Code release for Open Domain Generalization with Domain-Augmented Meta-Learning (CVPR2021)
Python
27
star
43

Batch-Spectral-Shrinkage

Code release for Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning (NeurIPS 2019)
Python
24
star
44

StochNorm

Code release for NeurIPS 2020 paper "Stochastic Normalization"
Python
23
star
45

Transferable-Query-Selection

Code Release for "Transferable Query Selection for Active Domain Adaptation"(CVPR2021)
Python
22
star
46

few-shot

A lightweight library that implements state-of-the-art few-shot learning algorithms.
Python
21
star
47

transferable-memory

Python
20
star
48

VideoDG

Python
20
star
49

Timer

Official code and checkpoints for "Timer: Transformers for Time Series Analysis at Scale"
Python
20
star
50

SPOT

Code release for "Supported Policy Optimization for Offline Reinforcement Learning" (NeurIPS 2022), https://arxiv.org/abs/2202.06239
Python
18
star
51

DPH

Code release for "Deep Priority Hashing" (ACMMM 2018)
C++
18
star
52

Decoupled-Adaptation-for-Cross-Domain-Object-Detection

Code for ICLR2022 Decoupled Adaptation for Cross-Domain Object Detection (D-adapt) https://arxiv.org/abs/2110.02578
17
star
53

TCL

Code release for Transferable Curriculum for Weakly-Supervised Domain Adaptation (AAAI2019)
Python
17
star
54

DCN

Deep Calibration Network
Python
16
star
55

MMHH

Python
15
star
56

PAN

Python
15
star
57

Metasets

Python
14
star
58

TAH

Code release for "Transfer Adversarial Hashing for Hamming Space Retrieval" (AAAI 2018)
C++
14
star
59

ForkMerge

Code release of paper "ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning" (NeurIPS 2023)
13
star
60

ModeRNN

Python
12
star
61

TransCal

Python
10
star
62

learn_torch.compile

torch.compile artifacts for common deep learning models, can be used as a learning resource for torch.compile
Python
9
star
63

Zoo-Tuning

Code release for Zoo-Tuning: Adaptive Transfer from A Zoo of Models (ICML2021)
Python
7
star
64

Regressive-Domain-Adaptation-for-Unsupervised-Keypoint-Detection

Code for CVPR 2021 Regressive Domain Adaptation for Unsupervised Keypoint Detection (RegDA) https://arxiv.org/abs/2103.06175
5
star
65

MitNet

About Code Release for "Estimating Heterogeneous Treatment Effects: Mutual Information Bounds and Learning Algorithms" (ICML 2023)
Python
3
star
66

TimeSiam

1
star