A symmetric graph autoencoder with a Laplacian-sharpening decoder, stabilized via signed graphs, improves unsupervised clustering and link prediction.
Note on the normalized laplacian eigenvalues of signed graphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning
A symmetric graph autoencoder with a Laplacian-sharpening decoder, stabilized via signed graphs, improves unsupervised clustering and link prediction.