Implicit deep learning has received increasing attention recently due to the fact that it generalizes the recursive prediction rules of many commonly used neural network architectures.
To address these limitations, we propose a teleport graph convolution layer (TeleGCL) that uses teleport functions to enable each node to aggregate information from a much larger neighborhood.
Based on our theoretical and empirical analysis, we propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
Ranked #2 on Node Classification on AMZ Computers
Use of attention operators on high-order data requires flattening of the spatial or spatial-temporal dimensions into a vector, which is assumed to follow a multivariate normal distribution.
To further reduce the requirements on computational resources, we propose the cGAO that performs attention operations along channels.
Ranked #8 on Graph Classification on PROTEINS
Another limitation of GCN when used on graph-based text representation tasks is that, GCNs do not consider the order information of nodes in graph.
Compared to prior CNNs designed for mobile devices, ChannelNets achieve a significant reduction in terms of the number of parameters and computational cost without loss in accuracy.
However, the number of neighboring units is neither fixed nor are they ordered in generic graphs, thereby hindering the applications of convolutional operations.
Ranked #2 on Document Classification on Cora
In this paper, we propose a set of methods based on kernel rotation and flip to enable rotation and flip invariance in convolutional neural networks.
In the simplest case, the proposed multi-stage VAE divides the decoder into two components in which the second component generates refined images based on the course images generated by the first component.
When used in image generation tasks, our PixelDCL can largely overcome the checkerboard problem suffered by regular deconvolution operations.