Radial Kernel Attention for Global Feature Exchange in Polymer Machine Learning Force Fields
Radial Kernel Attention provides a compact pathway for information exchange beyond local graph connectivity in polymer machine learning force fields, and improves all three metrics over UMA-S-1.2.1 on the same validation structures.
Wen-Bo Fu, Cheng-Hui Mao, Cheng-Wen Hu et al.
· 0 citations