Nature

Enhancing deep neural network training efficiency and performance through linear prediction

Deep neural networks have achieved remarkable success in various fields. However, training an effective deep neural network still poses challenges. This paper aims to propose a method to optimize the ...
Nature

Kolmogorov–Arnold graph neural networks for molecular property prediction

Graph neural networks (GNNs) have shown remarkable success in molecular property prediction as key models in geometric deep learning. Meanwhile, Kolmogorov–Arnold networks (KANs) have emerged as ...