Factorised Neural Relational Inference for Multi-Interaction Systems

05/21/2019
by   Ezra Webb, et al.
0

Many complex natural and cultural phenomena are well modelled by systems of simple interactions between particles. A number of architectures have been developed to articulate this kind of structure, both implicitly and explicitly. We consider an unsupervised explicit model, the NRI model, and make a series of representational adaptations and physically motivated changes. Most notably we factorise the inferred latent interaction graph into a multiplex graph, allowing each layer to encode for a different interaction-type. This fNRI model is smaller in size and significantly outperforms the original in both edge and trajectory prediction, establishing a new state-of-the-art. We also present a simplified variant of our model, which demonstrates the NRI's formulation as a variational auto-encoder is not necessary for good performance, and make an adaptation to the NRI's training routine, significantly improving its ability to model complex physical dynamical systems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/13/2018

Neural Relational Inference for Interacting Systems

Interacting systems are prevalent in nature, from dynamical systems in p...
research
05/29/2021

GINA: Neural Relational Inference From Independent Snapshots

Dynamical systems in which local interactions among agents give rise to ...
research
02/08/2022

Social-DualCVAE: Multimodal Trajectory Forecasting Based on Social Interactions Pattern Aware and Dual Conditional Variational Auto-Encoder

Pedestrian trajectory forecasting is a fundamental task in multiple util...
research
08/22/2016

LFADS - Latent Factor Analysis via Dynamical Systems

Neuroscience is experiencing a data revolution in which many hundreds or...
research
09/30/2020

The Role of Isomorphism Classes in Multi-Relational Datasets

Multi-interaction systems abound in nature, from colloidal suspensions t...
research
01/03/2020

Towards Automated Statistical Physics : Data-driven Modeling of Complex Systems with Deep Learning

Rich phenomena from complex systems have long intrigued researchers, and...
research
01/21/2023

Spatial Attention Kinetic Networks with E(n)-Equivariance

Neural networks that are equivariant to rotations, translations, reflect...

Please sign up or login with your details

Forgot password? Click here to reset