Decoupling Graph Convolutional Networks For Large-Scale Supervised Classification

We present a new approach to large-scale supervised heterogeneous graph classification. We decouple a large heterogeneous graph into smaller homogeneous ones. In this paper, we show that our model provides results close to the state-of-the-art model while greatly simplifying calculations and makes it possible to process complex heterogeneous graphs on a much larger scale. (C) 2020 The Authors. Published by Elsevier B.V.