Graph Convolutional Network (GCN)

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. Introduced by Kipf et al. in Semi-Supervised Classification with Graph Convolutional Networks

相关学科： Graph Convolutional NetworkNode ClassificationSkeleton Based Action RecognitionGATGraphSAGEGraph LearningGraph ClassificationGraph AttentionLink PredictionGraph Representation Learning

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

Rob Knight

318987 被引用，1171 篇论文

Albert-László Barabási

214997 被引用，510 篇论文

Jian Sun

179895 被引用，332 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

Jiawei Han

121361 被引用，1269 篇论文

Myrna M. Weissman

102201 被引用，846 篇论文

Jürgen Schmidhuber

101619 被引用，563 篇论文

Jian Yang

96983 被引用，1935 篇论文

Neil Gehrels

93243 被引用，992 篇论文