Factorised Neural Relational Inference for Multi-Interaction Systems
This work addresses the challenge of accurately modeling complex physical dynamical systems, though it is incremental as it builds on the existing NRI model.
The paper tackled the problem of modeling multi-interaction systems by factorizing the latent interaction graph into a multiplex graph, resulting in a model that is smaller and significantly outperforms the original in edge and trajectory prediction, establishing a new state-of-the-art.
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.