Sparse Diffusion-Convolutional Neural Networks


The predictive power and overall computational efficiency of Diffusionconvolutional neural networks make them an attractive choice for node classification tasks. However, a naive dense-tensor-based implementation of DCNNs leads to O(N) memory complexity which is prohibitive for large graphs. In this paper, we introduce a simple method for thresholding input… (More)


3 Figures and Tables

Slides referencing similar topics