This is a graph convolution implementation in Keras. Unlike CNN that does convolution among input sources regardless they are related or not, graph convolution only does convolution over related input ...

The Graph Diffusion Convolution (GDC) technique presented in this paper demonstrates how incorporating diffusion processes can enhance graph learning. By leveraging graph diffusion, GDC can ...

Graph convolution machine for context-aware recommender system. Higher Education Press . Journal Frontiers of Computer Science Funder National Key Research and Development Program of China, ...

In this paper, we present a novel convolution theorem which encompasses the well known convolution theorem in (graph) signal processing as well as the one related to time-varying filters. Specifically ...

4 Directed graph convolution neural networks for reward shaping. A DCN utilizes directed graph convolution to propagate messages α(S t) and β(S t). Here, we illustrate digraph Laplacian, network ...

In this article, a novel R-convolution kernel, named the fast quantum walk kernel (FQWK), is proposed for unattributed graphs. In FQWK, the similarity of the neighborhood-pair substructure between two ...