N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules

Abstract

Machine learning techniques have recently been adopted in various applications in medicine, biology, chemistry, and material engineering. An important task is to predict the properties of molecules, which serves as the main subroutine in many downstream applications such as virtual screening and drug design. Despite the increasing interest, the key challenge is to construct proper representations of molecules for learning algorithms. This paper introduces the N-gram graph, a simple unsupervised representation for molecules. The method first embeds the vertices in the molecule graph. It then constructs a compact representation for the graph by assembling the vertex embeddings in short walks in the graph, which we show is equivalent to a simple graph neural network that needs no training. The representations can thus be efficiently computed and then used with supervised learning methods for prediction. Experiments on 60 tasks from 10 benchmark datasets demonstrate its advantages over both popular graph neural networks and traditional representation methods. This is complemented by theoretical analysis showing its strong representation and prediction power.

arXiv comment28 pages. Accepted in NeurIPS 2019 as spotlight

Cited by in corpus (17)

• Self-Supervised Graph Transformer on Large-Scale Molecular Data
• Pre-training Molecular Graph Representation with 3D Geometry
• Generative Models for Automatic Chemical Design
• Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
• CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
• Multi-View Graph Neural Networks for Molecular Property Prediction
• Spherical Message Passing for 3D Graph Networks
• Learn molecular representations from large-scale unlabeled molecules for drug discovery
• Dual-view Molecule Pre-training
• Deep Graph Similarity Learning: A Survey
• Learning Attributed Graph Representations with Communicative Message Passing Transformer
• Cascade-BGNN: Toward Efficient Self-supervised Representation Learning on Large-scale Bipartite Graphs
• Neural Sentence Ordering Based on Constraint Graphs
• Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results
• Explaining Chemical Toxicity using Missing Features
• Weisfeiler-Lehman Embedding for Molecular Graph Neural Networks
• Deriving Visual Semantics from Spatial Context: An Adaptation of LSA and Word2Vec to generate Object and Scene Embeddings from Images