DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting

• URL: http://arxiv.org/abs/2608.20052v1
• Date: Thu, 20 Aug 2026 13:51:07 GMT
• Title: DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting
• Abstract summary: We propose DecoVAE, a lightweight interpretable trend-seasonal VAE framework.<n>It decomposes time series into trend and seasonal components by applying domain-specific inductive biases.<n>It consistently outperforms strong baselines in seven real-world benchmarks.
• Score: 43.38565681834944
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Probabilistic time series forecasting remains challenging, largely because modeling distinct trend and seasonal dynamics requires specialized approaches. Existing methods often fail to capture the unique inner properties of these components, lack interpretability, or suffer from heavy memory and runtime overhead. To address these limitations, we propose DecoVAE, a lightweight interpretable trend-seasonal VAE framework that explicitly decomposes time series into trend and seasonal components by applying domain-specific inductive biases. The trend stream enforces structural smoothness using a differential regularizer on the latent trajectory, analogous to the Hodrick-Prescott filter. Concurrently, the seasonal stream operates in the frequency domain via a complex Gaussian VAE, natively capturing the amplitude and phase of periodic patterns. Extensive evaluations across seven real-world benchmarks show that DecoVAE consistently outperforms strong baselines. It achieves reductions of up to 14.96\% in CRPS and 23.30\% in NMAE for short-term forecasting, and up to 52.68\% and 26.51\% for long-term horizons. Crucially, DecoVAE yields these accuracy gains while remaining highly efficient, reducing model weight by up to 93\% and accelerating speed by up to 74\% compared to the second-best method.

Related papers

• Rollcast: Proper-Score Gated Rolling Anchors for Adaptive Probabilistic Time-Series Forecasting [0.0]
  Rolling means, medians, extrema, regression endpoints, and quantiles define candidate forecast locations.<n>A state-dependent softmax gate learns anchor probabilities by minimizing negative log predictive density.<n>Recursive simulation propagates the resulting mixture over multiple forecast horizons.
  arXiv  Detail & Related papers  (2026-09-03T18:50:29Z)
• Learning to Difference: Adaptive Reversible Differencing (AdaRDiff) for Time Series Forecasting [2.370553892492642]
  Trends and seasonality introduce complex temporal structure that challenges learning-based forecasting models.<n>We propose textbfunderlineAdaptive textbfunderlineReversible textbfunderlineDifferencing textbf(AdaRDiff).<n>AdaRDiff attains state-of-the-art forecast accuracy across eight benchmarks spanning electricity, weather, traffic, and energy, at negligible parameter cost.
  arXiv  Detail & Related papers  (2026-08-28T09:51:08Z)
• CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting [37.52530836149578]
  We propose textitCLaST, a VAE framework for probabilistic time series forecasting.<n>CLaST learns embeddings that preserve contextual similarity between observations through our contrastive loss function.<n>In short-term forecasting tasks, our approach achieves improvements of up to $16.4%$ in CRPS and $14.4%$ in NMAE over the second-best method.<n>In long-term prediction CLaST attains superior overall performance by up to $48.6%$ and $25.1%$ in CRPS and NMAE, respectively.
  arXiv  Detail & Related papers  (2026-08-20T13:34:01Z)
• TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modeling [74.915718648935]
  Existing methods show limited accuracy gains and struggle with extreme events and error accumulation.<n>We propose a novel Triaxial State Space Model (TSSM) with a history-enhanced Temporal-VariableHistorical paradigm.<n>TSSM stacks historical samples into period-aligned batches, where forecasting is causally supported by historical and current observations.
  arXiv  Detail & Related papers  (2026-07-14T07:36:19Z)
• RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting [83.06074370551887]
  A fixed context window is mismatched to the time-varying optimal look-back of non-stationary price processes.<n>We propose a Mixture-of-Experts framework designed to adaptively determine the temporal context for each input sample.<n> Experiments on cumulative log-return prediction (HS300, S&P500) and fund sales forecasting demonstrate that RAVEN achieves SOTA performances, improves Pearson correlation by 9.2% on HS300 and 20.2% on S&P500, and reduces MSE by 18.2% on fund sales forecasting.
  arXiv  Detail & Related papers  (2026-06-23T02:11:04Z)
• Tyche: One Step Flow for Efficient Probabilistic Weather Forecasting [48.263481135566316]
  We present Tyche, a one-step conditional flow model for efficient probabilistic weather forecasting.<n>Experiments on ERA5 at 1.5$circ$ and 6-hour resolution show that our Tyche, using merely a single NFE, matches or exceeds the forecast skill and calibration of state-of-the-art multi-step generative baselines.
  arXiv  Detail & Related papers  (2026-05-07T20:25:28Z)
• Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking [51.56484100374058]
  We evaluate whether a fully automatic, purely feedback-driven ESN can serve as a competitive alternative to widely used statistical forecasting methods.<n>Forecast accuracy is measured using MASE and sMAPE and benchmarked against simple benchmarks like drift and seasonal naive and statistical models.
  arXiv  Detail & Related papers  (2026-02-03T16:01:22Z)
• A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting [81.73338008264115]
  Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers.<n>We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series.<n>Fire consistently outperforms state-of-the-art models on long-term forecasting benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T09:59:25Z)
• Swift: An Autoregressive Consistency Model for Efficient Weather Forecasting [0.8503925197267593]
  We introduce Swift, a single-step consistency model that enables autoregressive finetuning of a probability flow model.<n>Results show that Swift produces skillful 6-hourly forecasts that remain stable for up to 75 days, running $39times$ faster than state-of-the-art diffusion baselines.
  arXiv  Detail & Related papers  (2025-09-30T00:54:24Z)
• Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Model [55.25659103706409]
  This framework achieves state-of-the-art performance for our designed foundation model, YingLong.<n>YingLong is a non-causal, bidirectional attention encoder-only transformer trained through masked token recovery.<n>We release four foundation models ranging from 6M to 300M parameters, demonstrating superior results in zero-shot tasks.
  arXiv  Detail & Related papers  (2025-05-20T14:31:06Z)
• A Multi-scale Representation Learning Framework for Long-Term Time Series Forecasting [6.344911113059126]
  Long-term time series forecasting (LTSF) offers broad utility in practical settings like energy consumption and weather prediction.<n>This work confronts key issues in LTSF, including the suboptimal use of multi-granularity information.<n>Our method adeptly disentangles complex temporal dynamics using clear, concurrent predictions across various scales.
  arXiv  Detail & Related papers  (2025-05-13T03:26:44Z)
• CANet: ChronoAdaptive Network for Enhanced Long-Term Time Series Forecasting under Non-Stationarity [0.0]
  We introduce a novel architecture, ChoronoAdaptive Network (CANet), inspired by style-transfer techniques.<n>The core of CANet is the Non-stationary Adaptive Normalization module, seamlessly integrating the Style Blending Gate and Adaptive Instance Normalization (AdaIN)<n> experiments on real-world datasets validate CANet's superiority over state-of-the-art methods, achieving a 42% reduction in MSE and a 22% reduction in MAE.
  arXiv  Detail & Related papers  (2025-04-24T20:05:33Z)
• HADL Framework for Noise Resilient Long-Term Time Series Forecasting [0.7810572107832383]
  Long-term time series forecasting is critical in domains such as finance, economics, and energy.<n>The impact of temporal noise in extended lookback windows remains underexplored, often degrading model performance and computational efficiency.<n>We propose a novel framework that addresses these challenges by integrating the Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT)<n>Our approach demonstrates competitive robustness to noisy input, significantly reduces computational complexity, and achieves competitive or state-of-the-art forecasting performance across diverse benchmark datasets.
  arXiv  Detail & Related papers  (2025-02-14T21:41:42Z)

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.