Adaptive Graph Convolutional Neural Networks

doi:10.1609/aaai.v32i1.11691

Adaptive Graph Convolutional Neural Networks

2018-04-29

0

OA

AI

DOI：10.1609/aaai.v32i1.11691

原文链接

原文求助

摘要

En 中文

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and connectivity. The paper proposes a generalized and flexible graph CNN taking data of arbitrary graph structure as input. In that way a task-driven adaptive graph is learned for each graph data while training. To efficiently learn the graph, a distance metric learning is proposed. Extensive experiments on nine graph-structured datasets have demonstrated the superior performance improvement on both convergence speed and predictive accuracy.

Adaptive Graph Convolutional Neural Networks

摘要

期刊

机构

引用论文