Relational State-Space Model for Stochastic Multi-Object Systems
arXiv:2001.04050
Abstract
Real-world dynamical systems often consist of multiple stochastic subsystems that interact with each other. Modeling and forecasting the behavior of such dynamics are generally not easy, due to the inherent hardness in understanding the complicated interactions and evolutions of their constituents. This paper introduces the relational state-space model (R-SSM), a sequential hierarchical latent variable model that makes use of graph neural networks (GNNs) to simulate the joint state transitions of multiple correlated objects. By letting GNNs cooperate with SSM, R-SSM provides a flexible way to incorporate relational information into the modeling of multi-object dynamics. We further suggest augmenting the model with normalizing flows instantiated for vertex-indexed random variables and propose two auxiliary contrastive objectives to facilitate the learning. The utility of R-SSM is empirically evaluated on synthetic and real time-series datasets.
Accepted by ICLR 2020
References in corpus (19)
- Auto-Encoding Variational Bayes
- Sequence to Sequence Learning with Neural Networks
- Neural Message Passing for Quantum Chemistry
- Variational Inference with Normalizing Flows
- A Recurrent Latent Variable Model for Sequential Data
- Interaction Networks for Learning about Objects, Relations and Physics
- Learning Latent Dynamics for Planning from Pixels
- Learning Stochastic Recurrent Networks
- A Compositional Object-Based Approach to Learning Physical Dynamics
- Multiple Futures Prediction
- Invariant and Equivariant Graph Networks
- Auto-Encoding Sequential Monte Carlo
- Learning and Querying Fast Generative Models for Reinforcement Learning
- Emerging Convolutions for Generative Normalizing Flows
- Variational Graph Recurrent Neural Networks
- Stochastic Prediction of Multi-Agent Interactions from Partial Observations
- State Space LSTM Models with Particle MCMC Inference
- A General Method for Amortizing Variational Filtering
- Scalable Bayesian Learning for State Space Models using Variational Inference with SMC Samplers