Relational Graph Attention Networks
This work addresses the need for relational graph models in domains like molecular property prediction, but it is incremental as it builds on existing graph attention methods.
The paper tackled the problem of extending graph attention mechanisms to incorporate relational information, but found that Relational Graph Attention Networks performed worse than expected, with only marginal benefits for modeling molecular properties.
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.