Excited to present Matrix Function Networks (MFNs), our new non-local GNN architecture that parameterizes many-body non-local effects using the spectrum of learnable graph operators. MFNs' structured non-locality outperforms global attention. https://t.co/JrcuDN6NZ0 https://t.co/GGyUCyIai7
— Ilyes Batatia (@IlyesBatatia) Nov 3, 2023
from Twitter https://twitter.com/IlyesBatatia
November 03, 2023 at 09:37AM
via IFTTT
No comments:
Post a Comment