mlsanityData to 7 Oct 2026

Hybrid Variational Autoencoder for Time Series Forecasting

arXiv 2303.07048 ↗First posted 13 Mar 2023cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Variational autoencoders (VAE) are powerful generative models that learn the latent representations of input data as random variables. Recent studies show that VAE can flexibly learn the complex temporal dynamics of time series and achieve more promising forecasting results than deterministic models. However, a major limitation of existing works is that they fail to jointly learn the local patterns (e.g., seasonality and trend) and temporal dynamics of time series for forecasting. Accordingly, we propose a novel hybrid variational autoencoder (HyVAE) to integrate the learning of local patterns and temporal dynamics by variational inference for time series forecasting. Experimental results on four real-world datasets show that the proposed HyVAE achieves better forecasting results than various counterpart methods, as well as two HyVAE variants that only learn the local patterns or temporal dynamics of time series, respectively.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 15 of its 39 references that are in the map. First posted on arXiv 13 Mar 2023.

Builds on

15 of 39 references.

References · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  5. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  6. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  7. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 385
  8. 2016Ladder Variational Autoencoderscited by 315
  9. 2015Semi-Supervised Learning with Ladder Networkscited by 246
  10. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  11. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  12. 2021Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecastingcited by 67
3 more
  1. 2017Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Datacited by 47
  2. 2018Deep Air Quality Forecasting Using Hybrid Deep Learning Frameworkcited by 33
  3. 2021Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecastingcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 3.

8 papers.

  1. 2024Time-Causal VAE: Robust Financial Time Series Generatorcited by 8
  2. 2025Multimodal Conditioned Diffusive Time Series Forecastingcited by 8
  3. 2025TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAEcited by 2
  4. 2025Zero-shot Load Forecasting for Integrated Energy Systems: A Large Language Model-based Framework with Multi-task Learningcited by 1
  5. 2026Diffusion Models for Adaptive Sequential Data Generationcited by 1
  6. 2026PAC-Bayesian Reconstruction Guarantees for Time Series Variational Autoencoderscited by 1
  7. 2025From Classical Probabilistic Latent Variable Models to Modern Generative AI: A Unified Perspectivecited by 0
  8. 2026DynG-Diff: A State-Aware Dynamic Guidance Diffusion Framework for Probabilistic Time Series Forecastingcited by 0