Topology adaptive graph convolutional networks

Jian Du

[0]

Shanghang Zhang

[0]

Guanhang Wu

[0]

José M. F. Moura

[0]

Soummya Kar

[0]

arXiv: Learning, Volume abs/1710.10370, 2018.

Cited by: 33|Views43

Keywords:

rectified linear unitdeep learningcomputational complexitygraph signal processingnovel graph convolutional networkMore(11+)

Weibo:

Topology adaptive graph convolutional network that implements in the vertex domain offers implement in the spectrum domain unifying graph convolutional neural networks in both the spectrum domain and the vertex domain

Abstract:

Convolution acts as a local feature extractor in convolutional neural networks (CNNs). However, the convolution operation is not applicable when the input data is supported on an irregular graph such as with social networks, citation networks, or knowledge graphs. This paper proposes the topology adaptive graph convolutional network (TAGC...More

Code:

Data:

Full Text

View via Publisher