DeepAI AI Chat
Log In Sign Up

Neural Relational Inference with Efficient Message Passing Mechanisms

by   Siyuan Chen, et al.

Many complex processes can be viewed as dynamical systems of interacting agents. In many cases, only the state sequences of individual agents are observed, while the interacting relations and the dynamical rules are unknown. The neural relational inference (NRI) model adopts graph neural networks that pass messages over a latent graph to jointly learn the relations and the dynamics based on the observed data. However, NRI infers the relations independently and suffers from error accumulation in multi-step prediction at dynamics learning procedure. Besides, relation reconstruction without prior knowledge becomes more difficult in more complex systems. This paper introduces efficient message passing mechanisms to the graph neural networks with structural prior knowledge to address these problems. A relation interaction mechanism is proposed to capture the coexistence of all relations, and a spatio-temporal message passing mechanism is proposed to use historical information to alleviate error accumulation. Additionally, the structural prior knowledge, symmetry as a special case, is introduced for better relation prediction in more complex systems. The experimental results on simulated physics systems show that the proposed method outperforms existing state-of-the-art methods.


page 1

page 2

page 3

page 4

page 5

page 6

page 8

page 9


Unbiased Heterogeneous Scene Graph Generation with Relation-aware Message Passing Neural Network

Recent scene graph generation (SGG) frameworks have focused on learning ...

Learning Modular Simulations for Homogeneous Systems

Complex systems are often decomposed into modular subsystems for enginee...

Equivariant Graph Mechanics Networks with Constraints

Learning to reason about relations and dynamics over multiple interactin...

Discovering Latent Representations of Relations for Interacting Systems

Systems whose entities interact with each other are common. In many inte...

Equivariant Graph Hierarchy-Based Neural Networks

Equivariant Graph neural Networks (EGNs) are powerful in characterizing ...

POSLAN: Disentangling Chat with Positional and Language encoded Post Embeddings

Most online message threads inherently will be cluttered and any new use...

HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics

We propose a method that leverages graph neural networks, multi-level me...

Code Repositories


Code for Neural Relational Inference with Efficient Message Passing Mechanisms (AAAI 2021).

view repo