DeepAI AI Chat
Log In Sign Up

Neural Message Passing on High Order Paths

by   Daniel Flam-Shepherd, et al.

Graph neural network have achieved impressive results in predicting molecular properties, but they do not directly account for local and hidden structures in the graph such as functional groups and molecular geometry. At each propagation step, GNNs aggregate only over first order neighbours, ignoring important information contained in subsequent neighbours as well as the relationships between those higher order connections. In this work, we generalize graph neural nets to pass messages and aggregate across higher order paths. This allows for information to propagate over various levels and substructures of the graph. We demonstrate our model on a few tasks in molecular property prediction.


page 1

page 2

page 3

page 4


Theory of Graph Neural Networks: Representation and Learning

Graph Neural Networks (GNNs), neural network architectures targeted to l...

Weisfeiler and Lehman Go Cellular: CW Networks

Graph Neural Networks (GNNs) are limited in their expressive power, stru...

Equivariant Graph Attention Networks for Molecular Property Prediction

Learning and reasoning about 3D molecular structures with varying size i...

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

The prediction of physicochemical properties from molecular structures i...

Directional Message Passing on Molecular Graphs via Synthetic Coordinates

Graph neural networks that leverage coordinates via directional message ...

Directed Graph Attention Neural Network Utilizing 3D Coordinates for Molecular Property Prediction

The prosperity of computer vision (CV) and natural language procession (...

Edge-based Tensor prediction via graph neural networks

Message-passing neural networks (MPNN) have shown extremely high efficie...