Hierarchical Inter-Message Passing for Learning on Molecular Graphs

Abstract

We present a hierarchical neural message passing architecture for learning on molecular graphs. Our model takes in two complementary graph representations: the raw molecular graph representation and its associated junction tree, where nodes represent meaningful clusters in the original graph, e.g., rings or bridged compounds. We then proceed to learn a molecule's representation by passing messages inside each graph, and exchange messages between the two representations using a coarse-to-fine and fine-to-coarse information flow. Our method is able to overcome some of the restrictions known from classical GNNs, like detecting cycles, while still being very efficient to train. We validate its performance on the ZINC dataset and datasets stemming from the MoleculeNet benchmark collection.

Published at the Graph Representation Learning and Beyond (GRL+) Workhop at ICML 2020

References in corpus (10)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• On representing chemical environments
• Fast Graph Representation Learning with PyTorch Geometric
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Residual Gated Graph ConvNets
• Benchmarking Graph Neural Networks
• Strategies for Pre-training Graph Neural Networks
• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
• Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
• Deep Graph Matching Consensus

Cited by in corpus (13)

• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
• From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
• Graph-Guided Network for Irregularly Sampled Multivariate Time Series
• Building powerful and equivariant graph neural networks with structural message-passing
• Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
• Weisfeiler and Lehman Go Cellular: CW Networks
• Graph convolutions that can finally model local structure
• Wasserstein Embedding for Graph Learning
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
• Breaking the Expressive Bottlenecks of Graph Neural Networks
• Improving Graph Property Prediction with Generalized Readout Functions
• Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining