Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning

We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoencoder has a newly designed decoder which builds a completely symmetric autoenco...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings / IEEE International Conference on Computer Vision s. 6518 - 6527
Hlavní autoři: Park, Jiwoong, Lee, Minsik, Chang, Hyung Jin, Lee, Kyuewang, Choi, Jin Young
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.10.2019
Témata:
Chebyshev approximation
Convolution
Decoding
Image reconstruction
Laplace equations
Smoothing methods
Task analysis
ISSN:2380-7504
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We propose a symmetric graph convolutional autoencoder which produces a low-dimensional latent representation from a graph. In contrast to the existing graph autoencoders with asymmetric decoder parts, the proposed autoencoder has a newly designed decoder which builds a completely symmetric autoencoder form. For the reconstruction of node features, the decoder is designed based on Laplacian sharpening as the counterpart of Laplacian smoothing of the encoder, which allows utilizing the graph structure in the whole processes of the proposed autoencoder architecture. In order to prevent the numerical instability of the network caused by the Laplacian sharpening introduction, we further propose a new numerically stable form of the Laplacian sharpening by incorporating the signed graphs. In addition, a new cost function which finds a latent representation and a latent affinity matrix simultaneously is devised to boost the performance of image clustering tasks. The experimental results on clustering, link prediction and visualization tasks strongly support that the proposed model is stable and outperforms various state-of-the-art algorithms.
ISSN:2380-7504
DOI:10.1109/ICCV.2019.00662