Diffusion-TS: Interpretable Diffusion for General Time Series Generation
Reviewed by Pithpith:UQYZWCNIopen to challenge →
read the original abstract
Denoising diffusion probabilistic models (DDPMs) are becoming the leading paradigm for generative models. It has recently shown breakthroughs in audio synthesis, time series imputation and forecasting. In this paper, we propose Diffusion-TS, a novel diffusion-based framework that generates multivariate time series samples of high quality by using an encoder-decoder transformer with disentangled temporal representations, in which the decomposition technique guides Diffusion-TS to capture the semantic meaning of time series while transformers mine detailed sequential information from the noisy model input. Different from existing diffusion-based approaches, we train the model to directly reconstruct the sample instead of the noise in each diffusion step, combining a Fourier-based loss term. Diffusion-TS is expected to generate time series satisfying both interpretablity and realness. In addition, it is shown that the proposed Diffusion-TS can be easily extended to conditional generation tasks, such as forecasting and imputation, without any model changes. This also motivates us to further explore the performance of Diffusion-TS under irregular settings. Finally, through qualitative and quantitative experiments, results show that Diffusion-TS achieves the state-of-the-art results on various realistic analyses of time series.
This paper has not been read by Pith yet.
Forward citations
Cited by 17 Pith papers
-
Quantum Generative Diffusion Model for Real-World Time Series
QDiffusion-TS is the first quantum generative diffusion model for time series, achieving ~44% lower Wasserstein distance on Apple and Amazon stock data and up to 71% better forecasting RMSE with ~1000x fewer parameter...
-
What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions
Introduces the task of counterfactual time series forecasting with textual conditions plus a text-attribution mechanism that improves accuracy by distinguishing mutable from immutable factors.
-
SDFlow: Similarity-Driven Flow Matching for Time Series Generation
SDFlow uses similarity-driven flow matching with low-rank manifold decomposition and a categorical posterior to generate high-fidelity long time series in VQ space without step-wise error accumulation.
-
Is Flow Matching Just Trajectory Replay for Sequential Data?
Flow matching on time series targets a closed-form nonparametric velocity field that is a similarity-weighted mixture of observed transition velocities, making neural models approximations to an ideal memory-augmented...
-
EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting
EMFusion applies conditional diffusion models with cross-attention and imputation sampling to deliver uncertainty-aware probabilistic forecasts for frequency-selective EMF data, outperforming baselines by 23.85% in CRPS.
-
RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models
A curated 142-billion-point real-world multivariate time series corpus improves zero-shot forecasting when combined with existing synthetic and univariate pretraining data across four foundation models.
-
SRT: Super-Resolution for Time Series via Disentangled Rectified Flow
SRT decomposes low-resolution time series into trend and seasonal components, aligns them via implicit neural representations, and uses cross-resolution attention within a disentangled rectified flow to generate high-...
-
PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
PrismFlow augments flow matching with residual dynamical experts and a winner-take-all objective to reduce spectral distortion and improve mode coverage in time-series generation.
-
TGSD: Topology-Guided State-Space Diffusion Framework for EEG Spatial Super-Resolution
TGSD combines a Hierarchical Spatial Prior Encoder with conditional state-space diffusion to achieve EEG spatial super-resolution, outperforming baselines on reconstruction fidelity and classification on SEED and Phys...
-
SDFlow: Similarity-Driven Flow Matching for Time Series Generation
SDFlow learns a global transport map via similarity-driven flow matching in VQ latent space, using low-rank manifold decomposition and a categorical posterior to handle discreteness, yielding SOTA long-horizon perform...
-
Non-stationary Diffusion For Probabilistic Time Series Forecasting
NsDiff combines a denoising diffusion conditional generative model with a pre-trained mean/variance estimator and an uncertainty-aware noise schedule based on the Location-Scale Noise Model to capture time-varying unc...
-
MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition
MOSAIC structures LLM-based model selection via memory-grounded blueprints and failure-aware RL, reporting gains in performance and traceability on financial time-series tasks over AutoML and agent baselines.
-
High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework
Hybrid CoMeTS-GAN plus diffusion model generates multivariate financial time series claimed to better reproduce stylized facts and inter-asset correlations than prior generative methods.
-
Generative Augmentation of Imbalanced Flight Records for Flight Diversion Prediction: A Multi-objective Optimisation Framework
Hyperparameter-optimized generative models augment scarce flight diversion records and substantially improve prediction accuracy over real data alone.
-
Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation
A temporal extension of TabDDPM generates coherent synthetic time-series sequences on the WISDM dataset that match real distributions and support downstream classification with macro F1 of 0.64.
-
MSDformer: Multi-scale Discrete Transformer For Time Series Generation
MSDformer introduces a multi-scale discrete transformer that tokenizes time series at multiple scales and models them autoregressively in discrete space, claiming superior performance over prior DTM methods with rate-...
-
Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting
PPM injects parametric structural priors into generative models via a learnable mapping to improve probabilistic forecasts on non-stationary MTS data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.