New tasks

SGD optimizer is set with momentum of 0.9. This is consistent with the choice of GA T where additive attention is used. Figure B.1: Ranking analysis for a new GNN design dimension Attention 14 B.2 Case Study: Link Prediction as a New Type of T asks Our GNN design framework is applicable to other graph learning tasks beyond node or graph classification tasks. Here we include additional results for link prediction tasks. The extended task space is shown in Figure B.2. Figure B.2: GNN task space for a new type of GNN tasks Link Prediction In Table C.1, we show the best GNN design that we discover for each task in the main manuscript.