Timezone: »

 
Poster
Equivariant Graph Hierarchy-Based Neural Networks
Jiaqi Han · Wenbing Huang · Tingyang Xu · Yu Rong

@

Equivariant Graph neural Networks (EGNs) are powerful in characterizing the dynamics of multi-body physical systems. Existing EGNs conduct flat message passing, which, yet, is unable to capture the spatial/dynamical hierarchy for complex systems particularly, limiting substructure discovery and global information fusion. In this paper, we propose Equivariant Hierarchy-based Graph Networks (EGHNs) which consist of the three key components: generalized Equivariant Matrix Message Passing (EMMP) , E-Pool and E-UnPool. In particular, EMMP is able to improve the expressivity of conventional equivariant message passing, E-Pool assigns the quantities of the low-level nodes into high-level clusters, while E-UnPool leverages the high-level information to update the dynamics of the low-level nodes. As their names imply, both E-Pool and E-UnPool are guaranteed to be equivariant to meet physic symmetry. Considerable experimental evaluations verify the effectiveness of our EGHN on several applications including multi-object dynamics simulation, motion capture, and protein dynamics modeling.

Keywords: equivariant graph neural network
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Jiaqi Han (Tsinghua University)
Wenbing Huang (Tsinghua University)
Tingyang Xu (Tencent AI Lab)
Yu Rong (Shenzhen Tencent Computer System Co., Ltd.)

More from the Same Authors