Graph Models

Multiplex Molecular Graph Neural Network

Introduced by Zhang et al. in Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures

The Multiplex Molecular Graph Neural Network (MXMNet) is an approach for the representation learning of molecules. The molecular interactions are divided into two categories: local and global. Then a two-layer multiplex graph $G = \{ G_{l}, G_{g} \}$ is constructed for a molecule. In $G$, the local layer $G_{l}$ only contains the local connections that mainly capture covalent interactions, and the global layer $G_{g}$ contains the global connections that cover non-covalent interactions. MXMNet uses the Multiplex Molecular (MXM) module that contains a novel angle-aware message passing operated on $G_{l}$ and an efficient message passing operated on $G_{g}$.

Source: Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Drug Discovery 1 33.33%
Formation Energy 1 33.33%
Graph Neural Network 1 33.33%

Components


Component Type
MPNN
Graph Models

Categories