Recently, message-passing Neural networks (MPNN) provide a promising tool for
dealing with molecular graphs and have achieved remarkable success in
facilitating the discovery and materials design with desired properties.
However, the classical MPNN methods also suffer from a limitation in capturing
the strong topological information hidden in molecular structures, such as
nonisomorphic graphs. To address this problem, this work proposes a Simplicial
Message Passing (SMP) framework to better capture the topological information
from molecules, which can break through the limitation within the vanilla
message-passing paradigm. In SMP, a generalized message-passing framework is
established for aggregating the information from arbitrary-order simplicial
complex, and a hierarchical structure is elaborated to allow information
exchange between different order simplices. We apply the SMP framework within
deep learning architectures for quantum-chemical properties prediction and
achieve state-of-the-art results. The results show that compared to traditional
MPNN, involving higher-order simplex can better capture the complex structure
of molecules and substantially enhance the performance of tasks. The SMP-based
model can provide a generalized framework for GNNs and aid in the discovery and
design of materials with tailored properties for various applications.

该论文提出了一种基于 Simplicial Message Passing 框架来处理分子结构的方法，其中包括用于量子化学性质预测的深度学习体系结构，并比传统的 MPNN 表现更好。