Neural Message Passing on High Order Paths
This addresses the problem of capturing local and hidden structures like functional groups in molecular graphs for researchers in computational chemistry and drug discovery, representing an incremental improvement over standard GNNs.
The paper tackles the limitation of graph neural networks (GNNs) in molecular property prediction by generalizing them to pass messages and aggregate across higher-order paths, allowing information to propagate over various graph levels and substructures, and demonstrates this on molecular property prediction tasks.
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.