2019-09-06T14:00:00Z session topic is session topic is Topology Adaptive Graph Convolutional Networks. Here is the abstract of the paper:
Spectral graph convolutional neural networks (CNNs) require approximation to the convolution to alleviate the computational complexity, resulting in performance loss. This paper proposes the topology adaptive graph convolutional network (TAGCN), a novel graph convolutional network defined in the vertex domain. We provide 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. The 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. Since no approximation to the convolution is needed, TAGCN exhibits better performance than existing spectral CNNs on a number of data sets and is also computationally simpler than other recent methods.
We take notes and prepare the discussion in a public GDoc, you are very welcome to ask questions or share your thoughts in it
The session lasts for one hour between 2019-09-06T14:00:00Z and 2019-09-06T15:00:00Z
For more details, see our repository on GitHub