A spectral graph convolution for signed directed graphs via magnetic Laplacian.
Taewook KoYoonhyuk ChoiChong-Kwon KimPublished in: Neural Networks (2023)
Keyphrases
- directed graph
- spectral graph
- theoretic framework
- random walk
- graph partitioning
- multiscale
- spectral graph partitioning
- directed acyclic graph
- image processing
- strongly connected
- similarity matrix
- graph structure
- pairwise
- sparse coding
- undirected graph
- information theoretic
- graph structures
- natural images
- co occurrence
- high dimensional
- social networks