Graph2TS: Structure-Controlled Time Series Generation via Quantile-Graph VAEs

• URL: http://arxiv.org/abs/2603.19970v1
• Date: Fri, 20 Mar 2026 14:12:11 GMT
• Title: Graph2TS: Structure-Controlled Time Series Generation via Quantile-Graph VAEs
• Abstract summary: We propose a structure-residual perspective on time-series generation, viewing temporal data as the combination of a structural backbone and residual dynamics.<n>By conditioning generation on structure rather than labels or metadata, the model preserves global temporal organization while enabling controlled variation.<n> Experiments on diverse datasets, including sunspot, electricity load, ECG, and EEG signals, demonstrate improved distributional fidelity, temporal alignment, and representativeness compared to diffusion- and GAN-based baselines.
• Score: 1.0499611180329804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although recent generative models can produce time series with close marginal distributions, they often face a fundamental tension between preserving global temporal structure and modeling stochastic local variations, particularly for highly volatile signals with weak or irregular periodicity. Direct distribution matching in such settings can amplify noise or suppress meaningful temporal patterns. In this work, we propose a structure-residual perspective on time-series generation, viewing temporal data as the combination of a structural backbone and stochastic residual dynamics, thereby motivating the separation of global organization from sample-level variability. Based on this insight, we represent time-series structure using a quantile-based transition graph that compactly captures global distributional and temporal dependencies. Building on this representation, we propose Graph2TS, a quantile-graph conditioned variational autoencoder that performs cross-modal generation from structural graphs to time series. By conditioning generation on structure rather than labels or metadata, the model preserves global temporal organization while enabling controlled stochastic variation. Experiments on diverse datasets, including sunspot, electricity load, ECG, and EEG signals, demonstrate improved distributional fidelity, temporal alignment, and representativeness compared to diffusion- and GAN-based baselines, highlighting structure-controlled and cross-modal generation as a promising direction for time-series modeling.

Related papers

• REGEN: Reference-Guided Synthetic Multivariate Time Series Generation for Forecasting [7.771378647684901]
  We propose a reference-guided generative pipeline that treats observed sequences as structural scaffolds for synthesis.<n>We show that ReGeN-generated data consistently substitutes for real sibling data with minimal forecasting degradation.<n>This suggests that in low-data regimes, how reference data is structurally exploited can matter as much as how much data is available.
  arXiv  Detail & Related papers  (2026-06-03T16:19:55Z)
• Preserving Temporal Dynamics in Time Series Generation [0.2099922236065961]
  Time-series data augmentation plays a crucial role in regression-oriented forecasting tasks.<n>Existing approaches primarily focus on matching marginal data distributions.<n>We propose a model-agnostic Markov Chain Monte Carlo framework to mitigate distribution shift and preserve temporal dynamics.
  arXiv  Detail & Related papers  (2026-04-29T20:32:45Z)
• Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting [79.37674445572462]
  Time series forecasting (TSF) remains a challenging problem due to the intricate entanglement of intraperiod-fluctuations and interperiod-trends.<n>Treating reshaped tensors as static images results in a topological mismatch.<n> relying on uniform fixed-size representations allocates modeling capacity inefficiently.<n>TimeGS is a novel framework that fundamentally shifts the forecasting paradigm from regression to 2D generative rendering.
  arXiv  Detail & Related papers  (2026-02-10T14:13:36Z)
• DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters [50.43534351968113]
  Existing generative time series models do not address the multi-dimensional properties of time series data well.<n>Inspired by Multimodal Diffusion Transformers that integrate textual guidance into video generation, we propose Diffusion Transformers for Time Series (DiTS)
  arXiv  Detail & Related papers  (2026-02-06T10:48:13Z)
• UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting [90.47915032778366]
  We propose UniDiff, a unified diffusion framework for multimodal time series forecasting.<n>At its core lies a unified and parallel fusion module, where a single cross-attention mechanism integrates structural information from timestamps and semantic context from texts.<n>Experiments on real-world benchmark datasets across eight domains demonstrate that the proposed UniDiff model achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-08T05:36:14Z)
• PeriodNet: Boosting the Potential of Attention Mechanism for Time Series Forecasting [15.752636750230053]
  We present PeriodNet, which incorporates period attention and sparse period attention mechanism for analyzing adjacent periods.<n> PeriodNet achieves a relative improvement of 22% when forecasting time series with a length of 720, in comparison to other models based on the conventional encoder-decoder Transformer architecture.
  arXiv  Detail & Related papers  (2025-11-23T14:47:38Z)
• TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspective [6.771711398105306]
  Diffusion models have shown great promise in data generation, yet generating time series data remains challenging.<n>We present textitTSGDiff, a novel framework that rethinks time series generation from a graph-based perspective.<n>A graph neural network-based encoder-decoder architecture is employed to construct a latent space.
  arXiv  Detail & Related papers  (2025-11-15T11:58:25Z)
• TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation [0.31498833540989407]
  TIMED is a unified generative framework that captures global structure via a forward-reverse diffusion process.<n>To further align the real and synthetic distributions in feature space, TIMED incorporates a Maximum Mean Discrepancy (MMD) loss.<n>We show that TIMED generates more realistic and temporally coherent sequences than state-of-the-art generative models.
  arXiv  Detail & Related papers  (2025-09-23T23:05:40Z)
• Kuramoto Orientation Diffusion Models [67.0711709825854]
  Orientation-rich images, such as fingerprints and textures, often exhibit coherent angular patterns.<n>Motivated by the role of phase synchronization in biological systems, we propose a score-based generative model.<n>We implement competitive results on general image benchmarks and significantly improves generation quality on orientation-dense datasets like fingerprints and textures.
  arXiv  Detail & Related papers  (2025-09-18T18:18:49Z)
• Temporal Attention Evolutional Graph Convolutional Network for Multivariate Time Series Forecasting [2.6138578479379104]
  This paper introduces the Temporal Attention Evolutional Graph Convolutional Network (TAEGCN)<n>TAEGCN adeptly captures temporal causal relationships and hidden spatial dependencies within the data.<n> Experimental results conducted on two public transportation network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of the proposed model.
  arXiv  Detail & Related papers  (2025-05-01T04:50:00Z)
• MFRS: A Multi-Frequency Reference Series Approach to Scalable and Accurate Time-Series Forecasting [51.94256702463408]
  Time series predictability is derived from periodic characteristics at different frequencies.<n>We propose a novel time series forecasting method based on multi-frequency reference series correlation analysis.<n> Experiments on major open and synthetic datasets show state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-11T11:40:14Z)
• Timer-XL: Long-Context Transformers for Unified Time Series Forecasting [67.83502953961505]
  We present Timer-XL, a causal Transformer for unified time series forecasting.<n>Based on large-scale pre-training, Timer-XL achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2024-10-07T07:27:39Z)
• Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective [63.60312929416228]
  textbftextitAttraos incorporates chaos theory into long-term time series forecasting. We show that Attraos outperforms various LTSF methods on mainstream datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.
  arXiv  Detail & Related papers  (2024-02-18T05:35:01Z)
• Continuous-Time Bayesian Networks with Clocks [33.774970857450086]
  We introduce a set of node-wise clocks to construct a collection of graph-coupled semi-Markov chains. We provide algorithms for parameter and structure inference, which make use of local dependencies.
  arXiv  Detail & Related papers  (2020-07-01T09:33:39Z)

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.