mlsanityData to 7 Oct 2026

Disentangled Generative Models for Robust Prediction of System Dynamics

arXiv 2108.11684 ↗First posted 26 Aug 2021cs.LG cs.AI cs.NAcited by 8

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have become increasingly of interest in dynamical system prediction, but out-of-distribution generalization and long-term stability still remains challenging. In this work, we treat the domain parameters of dynamical systems as factors of variation of the data generating process. By leveraging ideas from supervised disentanglement and causal factorization, we aim to separate the domain parameters from the dynamics in the latent space of generative models. In our experiments we model dynamics both in phase space and in video sequences and conduct rigorous OOD evaluations. Results indicate that disentangled VAEs adapt better to domain parameters spaces that were not present in the training data. At the same time, disentanglement can improve the long-term and out-of-distribution predictions of state-of-the-art models in video sequences.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 26 of its 46 references that are in the map. First posted on arXiv 26 Aug 2021.

Builds on

26 of 46 references.

References · 26

  1. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  2. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  3. 2018Disentangling by Factorisingcited by 614
  4. 2019Machine Learning for Fluid Mechanicscited by 380
  5. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 273
  6. 2019Causality for Machine Learningcited by 242
  7. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
  8. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  9. 2018Recent Advances in Autoencoder-Based Representation Learningcited by 130
  10. 2020Dynamical Variational Autoencoders: A Comprehensive Reviewcited by 127
  11. 2018Disentangled Sequential Autoencodercited by 117
  12. 2018Discovering physical concepts with neural networkscited by 117
14 more
  1. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  2. 2016Disentangling factors of variation in deep representations using adversarial trainingcited by 87
  3. 2020Measuring Disentanglement: A Review of Metricscited by 69
  4. 2021Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modelingcited by 59
  5. 2019Disentangling Factors of Variation Using Few Labelscited by 57
  6. 2020A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluationcited by 52
  7. 2021Clockwork Variational Autoencoderscited by 40
  8. 2020Comparing recurrent and convolutional neural networks for predicting wave propagationcited by 15
  9. 2019Disentangled State Space Representationscited by 14
  10. 2019Customizing Sequence Generation with Multi-Task Dynamical Systemscited by 5
  11. 2020Deep Learning for Efficient Reconstruction of High-Resolution Turbulent DNS Datacited by 5
  12. 2020Real-time System Identification Using Deep Learning for Linear Processes with Application to Unmanned Aerial Vehiclescited by 3
  13. 2020Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural networkcited by 2
  14. 2021Joint Parameter Discovery and Generative Modeling of Dynamic Systemscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 5; 2025: 1.

8 papers.

  1. 2024Out-of-Domain Generalization in Dynamical Systems Reconstructioncited by 33
  2. 2024Learning Interpretable Hierarchical Dynamical Systems Models from Time Series Datacited by 14
  3. 2023PGODE: Towards High-quality System Dynamics Modelingcited by 7
  4. 2024Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidancecited by 5
  5. 2024System-Aware Neural ODE Processes for Few-Shot Bayesian Optimizationcited by 3
  6. 2024Disentangled Representation Learning for Parametric Partial Differential Equationscited by 2
  7. 2023Stretched and measured neural predictions of complex network dynamicscited by 1
  8. 2025Drivetrain simulation using variational autoencoderscited by 0