Symmetric graph convolutional autoencoder for unsupervised graph representation learning
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
Colleges, School and Institutes
- Seoul National University, Seoul, Korea.
- Hanyang University, Seoul, Korea
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.
|Title of host publication||Proceedings of the IEEE International Conference on Computer Vision (ICCV 2019)|
|Publication status||Accepted/In press - 22 Jul 2019|
|Event||IEEE International Conference on Computer Vision (ICCV 2019) - Seoul, Korea, Democratic People's Republic of|
Duration: 27 Oct 2019 → 2 Nov 2019
|Conference||IEEE International Conference on Computer Vision (ICCV 2019)|
|Country||Korea, Democratic People's Republic of|
|Period||27/10/19 → 2/11/19|