SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases

arXiv:2308.13212v2 Announce Type: replace
Abstract: Graph Neural Networks (GNNs) with equivariant properties have emerged as powerful tools for modeling complex dynamics of multi-object physical systems. However, their generalization ability is limited by the inadequate consideration of physical inductive biases: (1) Existing studies overlook the continuity of transitions among system states, opting to employ several discrete transformation layers to learn the direct mapping between two adjacent states; (2) Most models only account for first-order velocity information, despite the fact that many …

abstract arxiv biases continuity cs.ai cs.lg dynamics gnns graph graph neural networks however inductive modeling networks neural networks object studies systems tools transitions type