Extended Data Fig. 1: Test performance of Coord and Frad with different data accuracy on 3 tasks in QM9.
From: Pre-training with fractional denoising to enhance molecular property prediction
“Train from scratch" refers to the backbone model TorchMD-NET without pre-training. Both Coord and Frad use the TorchMD-NET backbone. “RDKit" and “DFT" refer to pre-training on molecular conformations generated by RDKit and DFT methods respectively. We can see that Frad is more robust to inaccurate pre-training conformations than Coord.
