Symmetric graph convolutional autoencoder for unsupervised graph representation learning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Authors

Colleges, School and Institutes

External organisations

  • Seoul National University, Seoul, Korea.
  • Hanyang University, Seoul, Korea

Abstract

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.

Details

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Computer Vision (ICCV 2019)
Publication statusAccepted/In press - 22 Jul 2019
EventIEEE International Conference on Computer Vision (ICCV 2019) - Seoul, Korea, Democratic People's Republic of
Duration: 27 Oct 20192 Nov 2019

Conference

ConferenceIEEE International Conference on Computer Vision (ICCV 2019)
CountryKorea, Democratic People's Republic of
CitySeoul
Period27/10/192/11/19