Supplementary Materials for SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection 1 Datasets

For the transductive setup, we used the three standard citation network benchmarks, Cora, Cite-seer and Pubmed (Sen et al., 2008). We followed the transductive setup adopted in (Y ang et al., Cora contains 2708 nodes, 5429 edges, 7 classes and 1433 features per node. Citeseer contains 3327 nodes, 4732 edges, 6 classes and 3703 features per node. Critically, testing graphs remain completely unobserved during training. The average number of nodes per graph is 2372.