Unified Training of Universal Time Series Forecasting Transformers
- URL: http://arxiv.org/abs/2402.02592v2
- Date: Wed, 22 May 2024 11:49:59 GMT
- Title: Unified Training of Universal Time Series Forecasting Transformers
- Authors: Gerald Woo, Chenghao Liu, Akshat Kumar, Caiming Xiong, Silvio Savarese, Doyen Sahoo,
- Abstract summary: We present a Masked-based Universal Time Series Forecasting Transformer (Moirai)
Moirai is trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains.
Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models.
- Score: 104.56318980466742
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models. The concept of universal forecasting, emerging from pre-training on a vast collection of time series datasets, envisions a single Large Time Series Model capable of addressing diverse downstream forecasting tasks. However, constructing such a model poses unique challenges specific to time series data: i) cross-frequency learning, ii) accommodating an arbitrary number of variates for multivariate time series, and iii) addressing the varying distributional properties inherent in large-scale data. To address these challenges, we present novel enhancements to the conventional time series Transformer architecture, resulting in our proposed Masked Encoder-based Universal Time Series Forecasting Transformer (Moirai). Trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains, Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models. Code, data, and model weights can be found at https://github.com/SalesforceAIResearch/uni2ts.
Related papers
- Sundial: A Family of Highly Capable Time Series Foundation Models [64.6322079384575]
We introduce Sundial, a family of native, flexible, and scalable time series foundation models.
Our model is pre-trained without specifying any prior distribution and can generate multiple probable predictions.
By mitigating mode collapse through TimeFlow Loss, we pre-train a family of Sundial models on TimeBench, which exhibit unprecedented model capacity and generalization performance.
arXiv Detail & Related papers (2025-02-02T14:52:50Z) - Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts [103.725112190618]
This paper introduces Moirai-MoE, using a single input/output projection layer while delegating the modeling of diverse time series patterns to the sparse mixture of experts.
Extensive experiments on 39 datasets demonstrate the superiority of Moirai-MoE over existing foundation models in both in-distribution and zero-shot scenarios.
arXiv Detail & Related papers (2024-10-14T13:01:11Z) - Timer-XL: Long-Context Transformers for Unified Time Series Forecasting [67.83502953961505]
We present Timer-XL, a generative Transformer for unified time series forecasting.
Timer-XL achieves state-of-the-art performance across challenging forecasting benchmarks through a unified approach.
arXiv Detail & Related papers (2024-10-07T07:27:39Z) - MOMENT: A Family of Open Time-series Foundation Models [19.0845213853369]
We introduce MOMENT, a family of open-source foundation models for general-purpose time series analysis.
We compile a collection of public time series, called the Time series Pile, and systematically tackle time series-specific challenges.
We build on recent work to design a benchmark to evaluate time series foundation models on diverse tasks and datasets in limited supervision settings.
arXiv Detail & Related papers (2024-02-06T10:48:46Z) - Timer: Generative Pre-trained Transformers Are Large Time Series Models [83.03091523806668]
This paper aims at the early development of large time series models (LTSM)
During pre-training, we curate large-scale datasets with up to 1 billion time points.
To meet diverse application needs, we convert forecasting, imputation, and anomaly detection of time series into a unified generative task.
arXiv Detail & Related papers (2024-02-04T06:55:55Z) - Lag-Llama: Towards Foundation Models for Probabilistic Time Series
Forecasting [54.04430089029033]
We present Lag-Llama, a general-purpose foundation model for time series forecasting based on a decoder-only transformer architecture.
Lag-Llama is pretrained on a large corpus of diverse time series data from several domains, and demonstrates strong zero-shot generalization capabilities.
When fine-tuned on relatively small fractions of such previously unseen datasets, Lag-Llama achieves state-of-the-art performance.
arXiv Detail & Related papers (2023-10-12T12:29:32Z) - Improving the Accuracy of Global Forecasting Models using Time Series
Data Augmentation [7.38079566297881]
Forecasting models that are trained across sets of many time series, known as Global Forecasting Models (GFM), have shown promising results in forecasting competitions and real-world applications.
We propose a novel, data augmentation based forecasting framework that is capable of improving the baseline accuracy of GFM models in less data-abundant settings.
arXiv Detail & Related papers (2020-08-06T13:52:20Z) - Deep Transformer Models for Time Series Forecasting: The Influenza
Prevalence Case [2.997238772148965]
Time series data are prevalent in many scientific and engineering disciplines.
We present a new approach to time series forecasting using Transformer-based machine learning models.
We show that the forecasting results produced by our approach are favorably comparable to the state-of-the-art.
arXiv Detail & Related papers (2020-01-23T00:22:22Z)
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.