TY - GEN
T1 - Symmetric graph convolutional autoencoder for unsupervised graph representation learning
AU - Park, Jiwoong
AU - Lee, Minsik
AU - Chang, Hyung Jin
PY - 2020/2/27
Y1 - 2020/2/27
N2 - 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-theart algorithms.
AB - 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-theart algorithms.
UR - http://openaccess.thecvf.com/ICCV2019.py
U2 - 10.1109/ICCV.2019.00662
DO - 10.1109/ICCV.2019.00662
M3 - Conference contribution
SN - 9781728148045
T3 - CVF International Conference on Computer Vision (ICCV)
SP - 6518
EP - 6527
BT - 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
PB - IEEE Computer Society
T2 - IEEE International Conference on Computer Vision (ICCV 2019)
Y2 - 27 October 2019 through 2 November 2019
ER -