The DOI matches its Crossref record, with a small difference in title or year.
One Fits All: Power General Time Series Analysis by Pretrained LM
Open accessAbstract
Although we have witnessed great success of pre-trained models in natural language processing (NLP) and computer vision (CV), limited progress has been made for general time series analysis. Unlike NLP and CV where a unified model can be used to perform different tasks, specially designed approach still dominates in each time series analysis task such as classification, anomaly detection, forecasting, and few-shot learning. 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. This model, known as the Frozen Pretrained Transformer (FPT), is evaluated through fine-tuning on all major types of tasks involving time series. Our results demonstrate that pre-trained models on natural language or images can lead to a comparable or state-of-the-art performance in all main time series analysis tasks, as illustrated in Figure 1. We also found both theoretically and empirically that the self-attention module behaviors similarly to principle component analysis (PCA), an observation that helps explains how transformer bridges the domain gap and a crucial step towards understanding the universality of a pre-trained transformer.The code is publicly available at https://github.com/DAMO-DI-ML/One_Fits_All.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“It refers to the another lightweight deep learning model that adopts purely fully connected layers for efficiency of HAR models on edge devices.”
From Towards Customizable Foundation Models for Human Activity Recognition with Wearable Devices (2025) · cites this paper as [70]
Citations
Cites
Still being checked.
Cited by
Sorted by citations
Zhou, H., Hu, C., Yuan, Y., Cui, Y., Jin, Y., Chen, C., Wu, H., Yuan, D., Jiang, L., Wu, D., et al. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3465447 · Cited by 344
Self-citationSpatial-Temporal Large Language Model for Traffic Prediction
Liu, C., Sun, Y., Xu, Q., Li, Z., Long, C., Li, Z., & Zhao, R. (2024) · IEEE International Conference on Mobile Data Management (MDM) · doi:10.1109/mdm61037.2024.00025 · Cited by 215
LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters
Chang, C., Wang, W., Peng, W.-C., & Chen, T.-F. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3719207 · Cited by 335
LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters
Chang, C., Wang, W.-Y., Peng, W.-C., & Chen, T.-F. (2023) · arXiv · doi:10.48550/arxiv.2308.08469 · Cited by 146
Deep Time Series Forecasting Models: A Comprehensive Survey
Liu, X., & Wang, W. (2024) · Mathematics · doi:10.3390/math12101504 · Cited by 152
Metadata
- Authors
- Zhou, T., Niu, P., Wang, X., Sun, L., & Jin, R.
- ORCID
- Niu, Peisong
- Venue
- Advances in Neural Information Processing Systems 36
- Published
- 2023
- Pages
- 43322-43355
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133215398
- Cited by
- 367
- References
- 0
- Citations by year
- 2026: 186 · 2025: 121 · 2024: 59 · 2023: 1
- FWCI
- 76.22
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- cc-by-nc-sa
- Locations
- neural information processing systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Energy Load and Power Forecasting
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Keywords
- time series forecasting, pre-trained language models, power systems, time series classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
