Procedural Pretraining for Molecular Property Prediction
Molecular property prediction is often limited by the small size of labeled downstream datasets, motivating pretraining on large corpora of unlabeled molecules. In this work, we ask whether useful inductive biases can instead be learned from abstract, procedurally generated data before a model sees any molecular data....
M. Friedemann, Zachary Shinnick, Philip H. S. Torr et al.
· 0 citations