A.1 EquivalencebetweenPreConvSAandvanillaSA OurproposedPreConvSAisformulatedinEquation1. f0i =MLPs fli fl+1

Inspired by the depthwise separable convolution used in MobileNet [1], we extend this separable idea to graph convolution. We only perform MLPs on point features directly to learn thechannelcorrelation, andleverages theanisotropic reduction toaggregatethespatial correlation.