GPS++: Reviving the Art of Message Passing for Molecular Property Prediction. (arXiv:2302.02947v2 [cs.LG] UPDATED)

We present GPS++, a hybrid Message Passing Neural Network / Graph Transformer
model for molecular property prediction. Our model integrates a well-tuned
local message passing component and biased global attention with other key
ideas from prior literature to achieve state-of-the-art results on large-scale
molecular dataset PCQM4Mv2. Through a thorough ablation study we highlight the
impact of individual components and find that nearly all of the model's
performance can be maintained without any use of global self-attention, showing
that message passing …

art arxiv attention dataset global global attention gps graph hybrid ideas literature network neural network prediction prior property scale state transformer transformer model