The first draw back is that it’s computational expensive because of the calculation of eigenvalue decomposition, which is $O(N^3)$ in time complexity, and the matrix multiplication, which is $O(N^2)$ in time complexity. 

The second drawback is that the transformation based on graph Laplacian matrix, so the parameters can’t be shared across different graphs. 


Drawbacks of fundamental Spectral Convolutional methods

Spectral convolution methods perform graph Fourier transformation on nodes and map to spectral domain, which involved conducting eigenvalue decomposition of graph Laplacian matrix.

University of Notre Dame

Convolution operations can be divided into two types:

1)	Spectral convolution

2)	Spatial convolution

3)	Mixture of spectral convolution and special convolution


Types of Convolution Operation

Zhang, Z., Cui, P., & Zhu, W. (2020). Deep learning on graphs: A survey. IEEE Transactions on Knowledge and Data Engineering.

Deep Learning on Graphs: A Survey

Spectral Convolution Methods

It performs convolution among neighbor nodes, which is based on connection relationship between nodes.

Learn Before

Related

Learn After