Topology adaptive graph convolutional networks
By Jian Du, Shanghang Zhang, Guanhang Wu, José M. F. Moura, Soummya Kar. arXiv.org, 2017
392 citations recorded by the source corpus.
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 (TAGCN), a novel graph convolutional network that generalizes CNN architectures to graph-structured data and provides a systematic way to design a set of fixed-size learnable filters to perform convolutions on graphs. The topologies of these filters are adaptive to the topology of the graph when they scan the graph to perform convolution, replacing the square filter for the grid-structured data in traditional CNNs. The outputs are the weighted sum of these filters’ outputs, extraction of both vertex features and strength of correlation between vertices. It can be used with both directed and undirected graphs. The proposed TAGCN not only inherits the properties of convolutions in CNN for grid-structured data, but it is also consistent with convolution as defined in graph signal processing. Further, as no approximation to the convolution is needed, TAGCN exhibits better performance than existing graph-convolution-approximation methods on a number of data sets. As only the polynomials of degree two of the adjacency matrix are used, TAGCN is also computationally simpler than other recent methods.
Subfields: Artificial Intelligence, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/0a5ecd6f9b58b827c06238b7ea4b22f0610e20a2
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Xinchao Wang
- Dacheng Tao
- Mingli Song
- Alejandro Ribeiro
- Fernando Gama
- Yiding Yang
- Geert Leus
- Antonio Garcia Marques
In Statistical and Nonlinear Physics
- Alejandro Ribeiro
- Fernando Gama
- Xinchao Wang
- Geert Leus
- Dacheng Tao
- Antonio Garcia Marques
- Yiding Yang
Citations in the corpus
- Distilling Knowledge From Graph Convolutional Networks (2020, background): “In recent years, graph convolutional network [9, 6, 21, 27, 10, 42] has been proved to be a powerful model for non-grid data, which is typically represented as a set of nodes with features along with a graph that represents the relationship among nodes.”
- Convolutional Neural Network Architectures for Signals Supported on Graphs (2018, background): “The difficulty of designing and implementing proper pooling is highlighted by the fact that several works exclude the pooling stage altogether [17], [20], [21], [23].”