Relational Graph Attention Networks

2019/04/11 by Dan Busbridge, Dane Sherburn, Busbridge, Dan +5 · 7 citations
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Complex Network Analysis Techniques #FOS: Computer and information sciences #Graph Theory and Algorithms #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1904.05811

openalex publication_date 2019/04/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We investigate Relational Graph Attention Networks, a class of models that extends non-relational graph attention mechanisms to incorporate relational information, opening up these methods to a wider variety of problems. A thorough evaluation of these models is performed, and comparisons are made against established benchmarks. To provide a meaningful comparison, we retrain Relational Graph Convolutional Networks, the spectral counterpart of Relational Graph Attention Networks, and evaluate them under the same conditions. We find that Relational Graph Attention Networks perform worse than anticipated, although some configurations are marginally beneficial for modelling molecular properties. We provide insights as to why this may be, and suggest both modifications to evaluation strategies, as well as directions to investigate for future work.

Citations

• Deep Convolutional Networks on Graph-Structured Data
• On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other
• Molecular graph convolutions: moving beyond fingerprints
• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric Deep Learning: Going beyond Euclidean data

Cited by

• Simple and Efficient Heterogeneous Temporal Graph Neural Network
• Interpretable Graph-Language Modeling for Detecting Youth Illicit Drug Use
• How Attentive are Graph Attention Networks?
• Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification
• Modeling Relational Logic Circuits for And-Inverter Graph Convolutional Network
• TLV-HGNN: Thinking Like a Vertex for Memory-efficient HGNN Inference
• R²-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation

Related

• Hierarchical Attention Models for Multi-Relational Graphs
• r-GAT: Relational Graph Attention Network for Multi-Relational Graphs
• Graph Attention Networks
• Conditional Graph Information Bottleneck for Molecular Relational Learning
• Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers