Improving Molecular Graph Neural Network Explainability
with Orthonormalization and Induced Sparsity
Ryan Henderson 1 Djork-Arne Clevert 1 Floriane Montanari 1
Abstract However, the opaque nature of artificial neural networks
has long been a stumbling block for wider adoption. In
Rationalizing which parts of a molecule drive the particular, the difficulty in extracting a straightforward ra-
predic ...


雷达卡




京公网安备 11010802022788号







