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

• URL: http://arxiv.org/abs/2409.02322v2
• Date: Tue, 11 Feb 2025 00:53:58 GMT
• Title: TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
• Authors: Defu Cao, Wen Ye, Yizhou Zhang, Yan Liu,
• Abstract summary: TimeDiT is a diffusion transformer model that combines temporal dependency learning with probabilistic sampling. TimeDiT employs a unified masking mechanism to harmonize the training and inference process across diverse tasks. Our systematic evaluation demonstrates TimeDiT's effectiveness both in fundamental tasks, i.e., forecasting and imputation, through zero-shot/fine-tuning.
• Score: 11.281386703572842
• License:
• Abstract: Foundation models, particularly Large Language Models (LLMs), have revolutionized text and video processing, yet time series data presents distinct challenges for such approaches due to domain-specific features such as missing values, multi-resolution characteristics, etc. Furthermore, the de-facto autoregressive transformers tend to learn deterministic temporal dependencies within pre-trained data while overlooking inherent uncertainties and lacking integration of physical constraints. In this paper, we introduce TimeDiT, a diffusion transformer model that synergistically combines transformer-based temporal dependency learning with diffusion-based probabilistic sampling. TimeDiT employs a unified masking mechanism to harmonize the training and inference process across diverse tasks while introducing a theoretically grounded, finetuning-free model editing strategy that enables flexible integration of external knowledge during sampling. Acknowledging the challenges of unifying multiple downstream tasks under a single model, our systematic evaluation demonstrates TimeDiT's effectiveness both in fundamental tasks, i.e., forecasting and imputation, through zero-shot/fine-tuning; and in domain tasks, i.e., multi-resolution forecasting, anomaly detection, and data generation, establishing it as a \textit{proto-foundation model} that bridges the gap between general-purpose and domain-specific models.

Related papers

• TiVaT: A Transformer with a Single Unified Mechanism for Capturing Asynchronous Dependencies in Multivariate Time Series Forecasting [4.733959271565453]
  TiVaT is a novel architecture incorporating a single unified module, a Joint-Axis (JA) attention module. The JA attention module dynamically selects relevant features to particularly capture asynchronous interactions. Extensive experiments demonstrate TiVaT's overall performance across diverse datasets.
  arXiv  Detail & Related papers  (2024-10-02T13:24:24Z)
• StreamEnsemble: Predictive Queries over Spatiotemporal Streaming Data [0.8437187555622164]
  We propose StreamEnembles, a novel approach to predictive queries overtemporal (ST) data distributions. Our experimental evaluation reveals that this method markedly outperforms traditional ensemble methods and single model approaches in terms of accuracy and time.
  arXiv  Detail & Related papers  (2024-09-30T23:50:16Z)
• Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift [40.734564394464556]
  We present a unified Probabilistic Graphical Model to Jointly capturing intra-/inter-series correlations and modeling the time-variant transitional distribution. We validate the effectiveness and efficiency of JointPGM through extensive experiments on six highly non-stationary MTS datasets.
  arXiv  Detail & Related papers  (2024-07-18T06:16:03Z)
• 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)
• Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values [67.76168547245237]
  We introduce a novel framework called GST-Pro, which utilizes a graphtemporal process and anomaly scorer to detect anomalies. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-11T10:10:16Z)
• 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)
• Multi-scale Attention Flow for Probabilistic Time Series Forecasting [68.20798558048678]
  We propose a novel non-autoregressive deep learning model, called Multi-scale Attention Normalizing Flow(MANF) Our model avoids the influence of cumulative error and does not increase the time complexity. Our model achieves state-of-the-art performance on many popular multivariate datasets.
  arXiv  Detail & Related papers  (2022-05-16T07:53:42Z)
• TACTiS: Transformer-Attentional Copulas for Time Series [76.71406465526454]
  estimation of time-varying quantities is a fundamental component of decision making in fields such as healthcare and finance. We propose a versatile method that estimates joint distributions using an attention-based decoder. We show that our model produces state-of-the-art predictions on several real-world datasets.
  arXiv  Detail & Related papers  (2022-02-07T21:37:29Z)
• 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)
• Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows [8.859284959951204]
  Time series forecasting is fundamental to scientific and engineering problems. Deep learning methods are well suited for this problem. We show that it improves over the state-of-the-art for standard metrics on many real-world data sets.
  arXiv  Detail & Related papers  (2020-02-14T16:16:51Z)

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.