NuwaTS: a Foundation Model Mending Every Incomplete Time Series
- URL: http://arxiv.org/abs/2405.15317v3
- Date: Wed, 02 Oct 2024 14:34:08 GMT
- Title: NuwaTS: a Foundation Model Mending Every Incomplete Time Series
- Authors: Jinguo Cheng, Chunwei Yang, Wanlin Cai, Yuxuan Liang, Qingsong Wen, Yuankai Wu,
- Abstract summary: We present textbfNuwaTS, a novel framework that repurposes Pre-trained Language Models for general time series imputation.
NuwaTS can be applied to impute missing data across any domain.
We show that NuwaTS generalizes to other time series tasks, such as forecasting.
- Score: 24.768755438620666
- License:
- Abstract: Time series imputation is critical for many real-world applications and has been widely studied. However, existing models often require specialized designs tailored to specific missing patterns, variables, or domains which limits their generalizability. In addition, current evaluation frameworks primarily focus on domain-specific tasks and often rely on time-wise train/validation/test data splits, which fail to rigorously assess a model's ability to generalize across unseen variables or domains. In this paper, we present \textbf{NuwaTS}, a novel framework that repurposes Pre-trained Language Models (PLMs) for general time series imputation. Once trained, NuwaTS can be applied to impute missing data across any domain. We introduce specialized embeddings for each sub-series patch, capturing information about the patch, its missing data patterns, and its statistical characteristics. By combining contrastive learning with the imputation task, we train PLMs to create a versatile, one-for-all imputation model. Additionally, we employ a plug-and-play fine-tuning approach, enabling efficient adaptation to domain-specific tasks with minimal adjustments. To evaluate cross-variable and cross-domain generalization, we propose a new benchmarking protocol that partitions the datasets along the variable dimension. Experimental results on over seventeen million time series samples from diverse domains demonstrate that NuwaTS outperforms state-of-the-art domain-specific models across various datasets under the proposed benchmarking protocol. Furthermore, we show that NuwaTS generalizes to other time series tasks, such as forecasting. Our codes are available at https://github.com/Chengyui/NuwaTS.
Related papers
- General Time-series Model for Universal Knowledge Representation of Multivariate Time-Series data [61.163542597764796]
We show that time series with different time granularities (or corresponding frequency resolutions) exhibit distinct joint distributions in the frequency domain.
A novel Fourier knowledge attention mechanism is proposed to enable learning time-aware representations from both the temporal and frequency domains.
An autoregressive blank infilling pre-training framework is incorporated to time series analysis for the first time, leading to a generative tasks agnostic pre-training strategy.
arXiv Detail & Related papers (2025-02-05T15:20:04Z) - Federated Foundation Models on Heterogeneous Time Series [36.229082478423585]
Efforts are primarily focused on fusing cross-domain time series datasets to extract shared subsequences as tokens for training models on Transformer architecture.
This paper proposes a novel federated learning approach to address the heterogeneity in time series foundation models training, namely FFTS.
The newly learned time series foundation models achieve superior generalization capabilities on cross-domain time series analysis tasks, including forecasting, imputation, and anomaly detection.
arXiv Detail & Related papers (2024-12-12T03:38:01Z) - Towards Generalisable Time Series Understanding Across Domains [10.350643783811174]
We introduce a novel pre-training paradigm specifically designed to handle time series heterogeneity.
We propose a tokeniser with learnable domain signatures, a dual masking strategy, and a normalised cross-correlation loss.
Our code and pre-trained weights are available at https://www.oetu.com/oetu/otis.
arXiv Detail & Related papers (2024-10-09T17:09:30Z) - PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
We propose a.
Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns.
We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
arXiv Detail & Related papers (2024-06-04T13:51:08Z) - UniCL: A Universal Contrastive Learning Framework for Large Time Series Models [18.005358506435847]
Time-series analysis plays a pivotal role across a range of critical applications, from finance to healthcare.
Traditional supervised learning methods first annotate extensive labels for time-series data in each task.
This paper introduces UniCL, a universal and scalable contrastive learning framework designed for pretraining time-series foundation models.
arXiv Detail & Related papers (2024-05-17T07:47:11Z) - TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis [29.232543319667005]
This work studies the problem of time series analysis with generalist (or foundation) models.
We consider the simple strategy of discretely tokenizing time series data drawn from a myriad of datasets via self-supervision.
Our method, TOkenized Time Series EMbeddings (TOTEM), produces such generalist time series models with minimal or no fine-tuning.
arXiv Detail & Related papers (2024-02-26T09:11:12Z) - Large Pre-trained time series models for cross-domain Time series analysis tasks [20.228846068418765]
Large Pre-trained Time-series Models (LPTM) is a novel method of adaptive segmentation that automatically identifies optimal dataset-specific segmentation strategy during pre-training.
LPTM achieves superior forecasting and time-series classification results taking up to 40% less data and 50% less training time compared to state-of-art baselines.
arXiv Detail & Related papers (2023-11-19T20:16:16Z) - Adaptive Test-Time Personalization for Federated Learning [51.25437606915392]
We introduce a novel setting called test-time personalized federated learning (TTPFL)
In TTPFL, clients locally adapt a global model in an unsupervised way without relying on any labeled data during test-time.
We propose a novel algorithm called ATP to adaptively learn the adaptation rates for each module in the model from distribution shifts among source domains.
arXiv Detail & Related papers (2023-10-28T20:42:47Z) - UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series
Forecasting [59.11817101030137]
This research advocates for a unified model paradigm that transcends domain boundaries.
Learning an effective cross-domain model presents the following challenges.
We propose UniTime for effective cross-domain time series learning.
arXiv Detail & Related papers (2023-10-15T06:30:22Z) - Learning to Generalize across Domains on Single Test Samples [126.9447368941314]
We learn to generalize across domains on single test samples.
We formulate the adaptation to the single test sample as a variational Bayesian inference problem.
Our model achieves at least comparable -- and often better -- performance than state-of-the-art methods on multiple benchmarks for domain generalization.
arXiv Detail & Related papers (2022-02-16T13:21:04Z) - Improving QA Generalization by Concurrent Modeling of Multiple Biases [61.597362592536896]
Existing NLP datasets contain various biases that models can easily exploit to achieve high performances on the corresponding evaluation sets.
We propose a general framework for improving the performance on both in-domain and out-of-domain datasets by concurrent modeling of multiple biases in the training data.
We extensively evaluate our framework on extractive question answering with training data from various domains with multiple biases of different strengths.
arXiv Detail & Related papers (2020-10-07T11:18:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.