This critique will compare two papers listed below that we discussed in class on graph neural networks and their applications. Your critique should be 1-2 pages long, single spaced. Please submit your critique as a PDF via canvas. The papers are:
- Protein Interface Prediction using Graph Convolutional Networks
- Recipe for a General, Powerful, Scalable Graph Transformer
Please keep the following points in mind as you write your critique and address each in a separate section.
1. An overview of the general problem area these methods are addressing.
2. Briefly describe each method.
3. How were the methods evaluated?
4. What novel insights were obtained using these methods?
5. What are the strengths and weaknesses of each method?
Focus on the graph convolutional network from paper 1 that includes edge features, as described in Equation 2.