1 code implementation • 4 Nov 2022 • Ryien Hosseini, Filippo Simini, Austin Clyde, Arvind Ramanathan
The process of screening molecules for desirable properties is a key step in several applications, ranging from drug discovery to material design.
1 code implementation • 20 Jul 2022 • Ryien Hosseini, Filippo Simini, Venkatram Vishwanath
At a high level, we conclude that on NVIDIA systems: (1) confounding bottlenecks such as memory inefficiency often dominate runtime costs moreso than data sparsity alone, (2) native Pytorch operations are often as or more competitive than their Pytorch Geometric equivalents, especially at low to moderate levels of input data sparsity, and (3) many operations central to state-of-the-art GNN architectures have little to no optimization for sparsity.