TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:JNOIRDVYrecord.jsonopen to challenge →
read the original abstract
Recent work in synthetic data generation in the time-series domain has focused on the use of Generative Adversarial Networks. We propose a novel architecture for synthetically generating time-series data with the use of Variational Auto-Encoders (VAEs). The proposed architecture has several distinct properties: interpretability, ability to encode domain knowledge, and reduced training times. We evaluate data generation quality by similarity and predictability against four multivariate datasets. We experiment with varying sizes of training data to measure the impact of data availability on generation quality for our VAE method as well as several state-of-the-art data generation methods. Our results on similarity tests show that the VAE approach is able to accurately represent the temporal attributes of the original data. On next-step prediction tasks using generated data, the proposed VAE architecture consistently meets or exceeds performance of state-of-the-art data generation methods. While noise reduction may cause the generated data to deviate from original data, we demonstrate the resulting de-noised data can significantly improve performance for next-step prediction using generated data. Finally, the proposed architecture can incorporate domain-specific time-patterns such as polynomial trends and seasonalities to provide interpretable outputs. Such interpretability can be highly advantageous in applications requiring transparency of model outputs or where users desire to inject prior knowledge of time-series patterns into the generative model.
This paper has not been read by Pith yet.
Forward citations
Cited by 18 Pith papers
-
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.
-
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.
-
Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models
UniTok tokenizes time series for an off-the-shelf LLM foundation model that unifies forecasting, generation, and classification through next-token prediction and training-free inference.
-
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-...
-
Universal Time Series Generation with Neural Controlled Differential Equations
Proves SLiCEs are universal time-series generators approximating path laws in W_∞ and proposes G-SLiCEs for path-space flow matching with benefits on irregular grids.
-
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.
-
GenTS: A Comprehensive Benchmark Library for Generative Time Series Models
GenTS is a modular benchmark library providing unified data pipelines, generative models, and evaluation metrics for time series synthesis, forecasting, and imputation, with open-source code and initial benchmarking e...
-
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...
-
GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables
GCGNet uses a variational generator, graph structure aligner, and graph refiner to jointly capture temporal and channel correlations in time series forecasting with exogenous variables, outperforming baselines on 12 r...
-
Cyclic Adaptive Private Synthesis for Sharing Real-World Data in Education
CAPS provides an iterative differentially private synthesis method that outperforms one-shot baselines on authentic educational real-world data.
-
UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation
UPLOTS proposes a unified prompt-guided pretrained transformer for generating constrained time-series data across diverse domains using dynamic multi-dataset loss re-weighting.
-
Stochastic weather generators for high-frequency wind vector time series
Time VQ-VAE models generate daily wind vector series that reproduce diurnal volatility patterns but fail to match the distribution of extreme wind speeds.
-
Diffusion Models for Adaptive Sequential Data Generation
Introduces a sequential forward-backward diffusion framework that generates adapted time series by conditioning on prior history, with a parallelizable score-matching objective and statistical guarantees for ReLU networks.
-
E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generation
E4GEN is an explainable diffusion model using E-Activator, E-Predictor, and E-Control for extreme-event-aware time-series generation evaluated on six datasets.
-
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.
-
AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage
AutoReproduce is a multi-agent system using paper lineage to autonomously reproduce AI experiment code, with a new benchmark showing improvements over baselines in fidelity and execution.
-
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-...
-
TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation
TriHead-GAN is a GAN framework whose triple-head discriminator supervises distributional authenticity, cross-variable dependency via regression, and temporal smoothness via adjacent-difference prediction for carbon em...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.