# Disentangled State Space Representations

arXiv: https://arxiv.org/abs/1906.03255 · HTML: https://mlsanity.com/paper/1906.03255/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2019.

## Built on by (most cited first, 14 of 14)

- [Weakly Supervised Representation Learning with Sparse Perturbations](https://mlsanity.com/paper/2206.01101/) (2022)
- [Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning](https://mlsanity.com/paper/2211.14666/) (2022)
- [Multifactor Sequential Disentanglement via Structured Koopman Autoencoders](https://mlsanity.com/paper/2303.17264/) (2023)
- [Dyn-O: Building Structured World Models with Object-Centric Representations](https://mlsanity.com/paper/2507.03298/) (2025)
- [Disentangled Generative Models for Robust Prediction of System Dynamics](https://mlsanity.com/paper/2108.11684/) (2021)
- [VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts](https://mlsanity.com/paper/2103.07292/) (2021)
- [Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling](https://mlsanity.com/paper/2103.08877/) (2021)
- [Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs](https://mlsanity.com/paper/2209.12590/) (2022)
- [SGW-based Multi-Task Learning in Vision Tasks](https://mlsanity.com/paper/2410.03778/) (2024)
- [Boxhead: A Dataset for Learning Hierarchical Representations](https://mlsanity.com/paper/2110.03628/) (2021)
- [Multi-Task Dynamical Systems](https://mlsanity.com/paper/2210.04023/) (2022)
- [Causal Dynamic Variational Autoencoder for Counterfactual Regression in Longitudinal Data](https://mlsanity.com/paper/2310.10559/) (2023)
- [Federated Causal Representation Learning in State-Space Systems for Decentralized Counterfactual Reasoning](https://mlsanity.com/paper/2602.19414/) (2026)
- [Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations](https://mlsanity.com/paper/2202.12932/) (2022)

## Abstract (arXiv)

Sequential data often originates from diverse domains across which statistical regularities and domain specifics exist. To specifically learn cross-domain sequence representations, we introduce disentangled state space models (DSSM) -- a class of SSM in which domain-invariant state dynamics is explicitly disentangled from domain-specific information governing that dynamics. We analyze how such separation can improve knowledge transfer to new domains, and enable robust prediction, sequence manipulation and domain characterization. We furthermore propose an unsupervised VAE-based training procedure to implement DSSM in form of Bayesian filters. In our experiments, we applied VAE-DSSM framework to achieve competitive performance in online ODE system identification and regression across experimental settings, and controlled generation and prediction of bouncing ball video sequences across varying gravitational influences.