Graph Convolutional Network

A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of convolutional neural networks which operate directly on graphs. The choice of convolutional architecture is motivated via a localized first-order approximation of spectral graph convolutions. The model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes.

相关学科： GCNNode ClassificationSkeleton Based Action RecognitionAction RecognitionGraph LearningLink PredictionGraph ClassificationHyperspectral Image ClassificationKnowledge GraphsConvolution

学科讨论

暂无讨论内容，你可以

学科管理组

暂无学科课代表，你可以申请成为课代表

重要学者

Yoshua Bengio

429868 被引用，1063 篇论文

Rob Knight

318987 被引用，1171 篇论文

Hongfang Liu

139850 被引用，2666 篇论文

Paul M. Thompson

130061 被引用，2679 篇论文

Ramnik J. Xavier

124984 被引用，683 篇论文

Jian Yang

96983 被引用，1935 篇论文

Vince D. Calhoun

80051 被引用，1324 篇论文

Philip S. Yu

79752 被引用，1712 篇论文

Chao Zhang

79014 被引用，3257 篇论文

Serge Belongie

69826 被引用，330 篇论文