On-device streaming speech-to-text engine powered by deep learning.
Key parameters and specifications
Key parameters and specifications
Parameter
Value
Language
Python
Category
Models
Subcategory
Domain-specific models
Keywords
Timeseries
Stars
673
Forks
90
Contributors
2
Created date
2023-09-22
Updated date
2026-10-14
Stars in 1 day
0
Stars in 7 days
1
Rank
15,181
Previous rank
6,642
Rank change
-8,539
7-day stars rank
10,973
Previous 7-day stars rank
11,031
7-day stars rank change
58
Total stars rank
15,342
Previous total stars rank
15,308
Total stars rank change
-34
Country
China
README summary
One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight) Tian Zhou, Peisong Niu, Xue Wang, Liang Sun, Rong Jin, "One Fits All: Power General Time Series Analysis by Pretrained LM,", NeurIPS, 2023. [paper] The main challenge that blocks the development of pre-trained model for time series analysis is the lack of a large amount of data for training. In this work, we address this challenge by leveraging language or CV models, pre-trained from
billions of tokens, for time series analysis. Specifically, we refrain from altering the self-attention and feedforward layers of the residual blocks in the pre-trained language or image model. General Time Series Tasks The proposed method outperforms other models on most tasks, including long-term forecasting, short-term forecasting, classification, anomaly detection, imputation, and few-shot leanring, zero-short learning. Follow the instructions provided in the respective task folder. Citation If you find this repo useful, please cite our
paper. Further Reading Survey on Transformers in Time Series: Qingsong Wen, Tian Zhou, Chaoli Zhang, Weiqi Chen, Ziqing Ma, Junchi Yan, and Liang Sun. [paper] Contact If you have any question or want to use the code, please contact tian. Acknowledgement We appreciate the following github repos a lot for their valuable code base or datasets:
Frequently asked questions
How many stars and forks are recorded?
DAMO-DI-ML/NeurIPS2023-One-Fits-All has 673 stars and 90 forks.
What is the repository rank?
DAMO-DI-ML/NeurIPS2023-One-Fits-All is ranked 15,181.
What language and category are recorded?
DAMO-DI-ML/NeurIPS2023-One-Fits-All has 673 stars, uses Python and belongs to Models.
Which repository is closest in rank?
DAMO-DI-ML/NeurIPS2023-One-Fits-All is compared with inclusionAI/Ming, ranked 15,173 with 674 stars.
README
One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)
Tian Zhou, Peisong Niu, Xue Wang, Liang Sun, Rong Jin, "One Fits All: Power General Time Series Analysis by Pretrained LM,", NeurIPS, 2023. [paper]
The main challenge that blocks the development of pre-trained model for time series analysis is the lack of a large amount of data for training. In this work, we address this challenge by leveraging language or CV models, pre-trained from billions of tokens, for time series analysis. Specifically, we refrain from altering the self-attention and feedforward layers of the residual blocks in the pre-trained language or image model.
Follow the instructions provided in the respective task folder.
Citation
If you find this repo useful, please cite our paper.
@inproceedings{zhou2023onefitsall,
title={{One Fits All}: Power General Time Series Analysis by Pretrained LM},
author={Tian Zhou, Peisong Niu, Xue Wang, Liang Sun, Rong Jin},
booktitle={NeurIPS},
year={2023}
}
Further Reading
Survey on Transformers in Time Series:
Qingsong Wen, Tian Zhou, Chaoli Zhang, Weiqi Chen, Ziqing Ma, Junchi Yan, and Liang Sun. "Transformers in time series: A survey.", IJCAI, 2023. [paper]
