ORNL / HydraGNN

Distributed PyTorch implementation of multi-headed graph convolutional neural networks
BSD 3-Clause "New" or "Revised" License
68 stars 29 forks source link

Reformatting MACE #307

Closed RylieWeaver closed 2 weeks ago

RylieWeaver commented 2 weeks ago

Reworking of MACE for cleanliness, robustness to hyperparameter configurations, and numerical stability in decoders.

Main Changes:

(1) Many changes to cleanliness and comments, moving some blocks to the utils. (2) Handle configurations with only one convolutional layer where both first_layer and last_layer are true (3) Do not append multiple layers in the decoder block when doing a purely linear decoding. This is because multiple linear layers stacked on top of each other without activations can be cause more erratic training / numerical instability.