TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model

• URL: http://arxiv.org/abs/2409.02322v1
• Date: Tue, 3 Sep 2024 22:31:57 GMT
• Title: TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
• Authors: Defu Cao, Wen Ye, Yizhou Zhang, Yan Liu,
• Abstract summary: A family of models have been developed, utilizing a temporal auto-regressive generative Transformer architecture. TimeDiT is a general foundation model for time series that employs a denoising diffusion paradigm instead of temporal auto-regressive generation. Extensive experiments conducted on a varity of tasks such as forecasting, imputation, and anomaly detection, demonstrate the effectiveness of TimeDiT.
• Score: 11.281386703572842
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: With recent advances in building foundation models for texts and video data, there is a surge of interest in foundation models for time series. A family of models have been developed, utilizing a temporal auto-regressive generative Transformer architecture, whose effectiveness has been proven in Large Language Models. While the empirical results are promising, almost all existing time series foundation models have only been tested on well-curated ``benchmark'' datasets very similar to texts. However, real-world time series exhibit unique challenges, such as variable channel sizes across domains, missing values, and varying signal sampling intervals due to the multi-resolution nature of real-world data. Additionally, the uni-directional nature of temporally auto-regressive decoding limits the incorporation of domain knowledge, such as physical laws expressed as partial differential equations (PDEs). To address these challenges, we introduce the Time Diffusion Transformer (TimeDiT), a general foundation model for time series that employs a denoising diffusion paradigm instead of temporal auto-regressive generation. TimeDiT leverages the Transformer architecture to capture temporal dependencies and employs diffusion processes to generate high-quality candidate samples without imposing stringent assumptions on the target distribution via novel masking schemes and a channel alignment strategy. Furthermore, we propose a finetuning-free model editing strategy that allows the seamless integration of external knowledge during the sampling process without updating any model parameters. Extensive experiments conducted on a varity of tasks such as forecasting, imputation, and anomaly detection, demonstrate the effectiveness of TimeDiT.

Related papers

• ODEStream: A Buffer-Free Online Learning Framework with ODE-based Adaptor for Streaming Time Series Forecasting [11.261457967759688]
  ODEStream is a buffer-free continual learning framework that incorporates a temporal isolation layer that integrates temporal dependencies within the data. Our approach focuses on learning how the dynamics and distribution of historical data change with time, facilitating the direct processing of streaming sequences. Evaluations on benchmark real-world datasets demonstrate that ODEStream outperforms the state-of-the-art online learning and streaming analysis baselines.
  arXiv  Detail & Related papers  (2024-11-11T22:36:33Z)
• 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)
• UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting [98.12558945781693]
  We propose a transformer-based model UniTST containing a unified attention mechanism on the flattened patch tokens. Although our proposed model employs a simple architecture, it offers compelling performance as shown in our experiments on several datasets for time series forecasting.
  arXiv  Detail & Related papers  (2024-06-07T14:39:28Z)
• PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations [49.80959046861793]
  We present PDETime, a novel LMTF model inspired by the principles of Neural PDE solvers. Our experimentation across seven diversetemporal real-world LMTF datasets reveals that PDETime adapts effectively to the intrinsic nature of the data.
  arXiv  Detail & Related papers  (2024-02-25T17:39:44Z)
• Unified Training of Universal Time Series Forecasting Transformers [104.56318980466742]
  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.
  arXiv  Detail & Related papers  (2024-02-04T20:00:45Z)
• TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting [24.834846119163885]
  We propose a novel framework, TEMPO, that can effectively learn time series representations. TEMPO expands the capability for dynamically modeling real-world temporal phenomena from data within diverse domains.
  arXiv  Detail & Related papers  (2023-10-08T00:02:25Z)
• Ti-MAE: Self-Supervised Masked Time Series Autoencoders [16.98069693152999]
  We propose a novel framework named Ti-MAE, in which the input time series are assumed to follow an integrate distribution. Ti-MAE randomly masks out embedded time series data and learns an autoencoder to reconstruct them at the point-level. Experiments on several public real-world datasets demonstrate that our framework of masked autoencoding could learn strong representations directly from the raw data.
  arXiv  Detail & Related papers  (2023-01-21T03:20:23Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)
• TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis [12.867257563413972]
  Time series anomaly detection is a challenging problem due to the complex temporal dependencies and the limited label data. We propose a Time-Frequency analysis based time series Anomaly Detection model, or TFAD, to exploit both time and frequency domains for performance improvement.
  arXiv  Detail & Related papers  (2022-10-18T09:08:57Z)
• Heteroscedastic Temporal Variational Autoencoder For Irregular Time Series [15.380441563675243]
  We propose a new deep learning framework for irregularly sampled time series that we call the Heteroscedastic Temporal Variational Autoencoder (HeTVAE) HeTVAE includes a novel input layer to encode information about input observation sparsity, a temporal VAE architecture to propagate uncertainty due to input sparsity, and a heteroscedastic output layer to enable variable uncertainty in output due to variables. Our results show that the proposed architecture is better able to reflect variable uncertainty through time sparse and irregular sampling than a range of baseline and traditional models, as well as recently proposed deep latent variable models that use
  arXiv  Detail & Related papers  (2021-07-23T16:59:21Z)
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder [59.69303945834122]
  We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series. Our model parameterizes mean and variance for each time-stamp with flexible neural networks. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
  arXiv  Detail & Related papers  (2021-02-02T06:15:15Z)

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.