- This paper introduces Graph Attention Networks (GATs), a novel neural network architecture based on masked self-attention layers for graph-structured data.
- Focus of this paper was to compare between RNN and ConvNet architectures on two basic graph problems: Subgraph Matching and Semi-Supervised Clustering, in the variable graph setting.
As part of my coursework at NTU, I will be doing research on the topic of Semi-Supervised Clustering with Graph Neural Networks under Prof Xavier Bresson.