Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks in Molecular Graph Analysis

2019/02/04 by Katsuhiko Ishiguro, Ishiguro, Katsuhiko, Shin‐ichi Maeda +3 · 1 citation
Computer Science · Materials Science · #Advanced Graph Neural Networks #Computational Drug Discovery Methods #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Materials Science

paper · pdf · doi:10.48550/arxiv.1902.01020

openalex publication_date 2019/02/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Graph Neural Network (GNN) is a popular architecture for the analysis of chemical molecules, and it has numerous applications in material and medicinal science. Current lines of GNNs developed for molecular analysis, however, do not fit well on the training set, and their performance does not scale well with the complexity of the network. In this paper, we propose an auxiliary module to be attached to a GNN that can boost the representation power of the model without hindering with the original GNN architecture. Our auxiliary module can be attached to a wide variety of GNNs, including those that are used commonly in biochemical applications. With our auxiliary architecture, the performances of many GNNs used in practice improve more consistently, achieving the state-of-the-art performance on popular molecular graph datasets.

Citations

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Molecular graph convolutions: moving beyond fingerprints
• Neural Message Passing for Quantum Chemistry
• Inductive Representation Learning on Large Graphs
• Relational Graph Attention Networks
• Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories

Cited by

• Weisfeiler-Lehman Embedding for Molecular Graph Neural Networks

Related

• Computing Graph Neural Networks: A Survey from Algorithms to Accelerators
• GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation
• Memory-Based Graph Networks
• MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation
• Image-Like Graph Representations for Improved Molecular Property\n Prediction