Relational Graph Attention Networks

Dan Busbridge, Dane Sherburn, Pietro Cavallo, Nils Y. Hammerla

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.

Keywords: RGCN, attention, graph convolutional networks, semi-supervised learning, graph classification, molecules

TL;DR: We propose a new model for relational graphs and evaluate it on relational transductive and inductive tasks.

Code: [ Babylonpartners/rgat](https://github.com/Babylonpartners/rgat) + [ 1 community implementation](https://paperswithcode.com/paper/?openreview=Bklzkh0qFm)

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:1904.05811/code)