Synthetic Series-Symbol Data Generation for Time Series Foundation Models

• URL: http://arxiv.org/abs/2510.08445v3
• Date: Mon, 20 Oct 2025 08:04:01 GMT
• Title: Synthetic Series-Symbol Data Generation for Time Series Foundation Models
• Abstract summary: Foundation models for time series analysis (TSA) have attracted significant attention.<n>Challenges such as training data scarcity and imbalance continue to hinder their development.<n>We design a series-symbol data generation mechanism, enabling the unrestricted creation of high-quality time series data.<n>To leverage series-symbol data pairs with strong correlations, we develop SymTime, a pre-trained foundation model for enhancing time series representation.
• Score: 18.504711221635606
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundation models for time series analysis (TSA) have attracted significant attention. However, challenges such as training data scarcity and imbalance continue to hinder their development. Inspired by complex dynamic system theories, we design a series-symbol data generation mechanism, enabling the unrestricted creation of high-quality time series data paired with corresponding symbolic expressions. To leverage series-symbol data pairs with strong correlations, we develop SymTime, a pre-trained foundation model for enhancing time series representation using symbolic information. SymTime demonstrates competitive performance across five major TSA tasks when fine-tunes with downstream tasks, rivaling foundation models pre-trained on real-world datasets. This approach underscores the potential of series-symbol data generation and pretraining mechanisms in overcoming data scarcity and enhancing task performance. The code is available at https://github.com/wwhenxuan/SymTime.

Related papers

• Synthetic Time Series Generation via Complex Networks [39.146761527401424]
  We present a framework for generating synthetic time series by leveraging complex networks mappings.<n>We investigate whether time series transformed into Quantile Graphs (QG) -- and then reconstructed via inverse mapping -- can produce synthetic data.<n>Results indicate that our quantile graph-based methodology offers a competitive and interpretable alternative for synthetic time series generation.
  arXiv  Detail & Related papers  (2026-01-30T12:01:50Z)
• OATS: Online Data Augmentation for Time Series Foundation Models [49.1394215208561]
  Time Series Foundation Models (TSFMs) are a powerful paradigm for time analysis and are often enhanced by synthetic data augmentation to improve the training data quality.<n>We propose OATS (Online Data Augmentation for Time Series Foundation Models), a principled strategy that generates synthetic data tailored to different training steps.
  arXiv  Detail & Related papers  (2026-01-26T23:51:03Z)
• FusAD: Time-Frequency Fusion with Adaptive Denoising for General Time Series Analysis [92.23551599659186]
  Time series analysis plays a vital role in fields such as finance, healthcare, industry, and meteorology.<n>FusAD is a unified analysis framework designed for diverse time series tasks.
  arXiv  Detail & Related papers  (2025-12-16T04:34:27Z)
• Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models [104.17057231661371]
  Time series analysis is crucial for understanding dynamics of complex systems.<n>Recent advances in foundation models have led to task-agnostic Time Series Foundation Models (TSFMs) and Large Language Model-based Time Series Models (TSLLMs)<n>Their success depends on large, diverse, and high-quality datasets, which are challenging to build due to regulatory, diversity, quality, and quantity constraints.<n>This survey provides a comprehensive review of synthetic data for TSFMs and TSLLMs, analyzing data generation strategies, their role in model pretraining, fine-tuning, and evaluation, and identifying future research directions.
  arXiv  Detail & Related papers  (2025-03-14T13:53:46Z)
• Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation [34.04850897522787]
  Foundation models for time series analysis (TSA) have attracted significant attention.<n> challenges such as data scarcity and data imbalance continue to hinder their development.<n>We introduce a series-symbol (S2) dual-modulity data generation mechanism, enabling the unrestricted creation of high-quality time series data.
  arXiv  Detail & Related papers  (2025-02-21T13:43:24Z)
• MTSA-SNN: A Multi-modal Time Series Analysis Model Based on Spiking Neural Network [23.303230721723278]
  We propose a Multi-modal Time Series Analysis Model Based on Spiking Neural Network (MTSA-SNN) The Pulse unifies the encoding of temporal images and sequential information in a common pulse-based representation. We incorporate wavelet transform operations to enhance the model's ability to analyze and evaluate temporal information.
  arXiv  Detail & Related papers  (2024-02-08T05:39:11Z)
• 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)
• MADS: Modulated Auto-Decoding SIREN for time series imputation [9.673093148930874]
  We propose MADS, a novel auto-decoding framework for time series imputation, built upon implicit neural representations. We evaluate our model on two real-world datasets, and show that it outperforms state-of-the-art methods for time series imputation.
  arXiv  Detail & Related papers  (2023-07-03T09:08:47Z)
• HyperTime: Implicit Neural Representation for Time Series [131.57172578210256]
  Implicit neural representations (INRs) have recently emerged as a powerful tool that provides an accurate and resolution-independent encoding of data. In this paper, we analyze the representation of time series using INRs, comparing different activation functions in terms of reconstruction accuracy and training convergence speed. We propose a hypernetwork architecture that leverages INRs to learn a compressed latent representation of an entire time series dataset.
  arXiv  Detail & Related papers  (2022-08-11T14:05:51Z)
• DAMNETS: A Deep Autoregressive Model for Generating Markovian Network Time Series [6.834250594353335]
  Generative models for network time series (also known as dynamic graphs) have tremendous potential in fields such as epidemiology, biology and economics. Here we introduce DAMNETS, a scalable deep generative model for network time series.
  arXiv  Detail & Related papers  (2022-03-28T18:14:04Z)
• Towards Generating Real-World Time Series Data [52.51620668470388]
  We propose a novel generative framework for time series data generation - RTSGAN. RTSGAN learns an encoder-decoder module which provides a mapping between a time series instance and a fixed-dimension latent vector. To generate time series with missing values, we further equip RTSGAN with an observation embedding layer and a decide-and-generate decoder.
  arXiv  Detail & Related papers  (2021-11-16T11:31:37Z)
• Time Series is a Special Sequence: Forecasting with Sample Convolution and Interaction [9.449017120452675]
  Time series is a special type of sequence data, a set of observations collected at even intervals of time and ordered chronologically. Existing deep learning techniques use generic sequence models for time series analysis, which ignore some of its unique properties. We propose a novel neural network architecture and apply it for the time series forecasting problem, wherein we conduct sample convolution and interaction at multiple resolutions for temporal modeling.
  arXiv  Detail & Related papers  (2021-06-17T08:15:04Z)

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.