Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning
This work addresses the problem of learning graph representations without labels, which is incremental as it builds on existing graph autoencoders by introducing symmetry and stability improvements.
The authors tackled unsupervised graph representation learning by proposing a symmetric graph convolutional autoencoder with a Laplacian sharpening decoder and a new cost function, achieving stable performance and outperforming state-of-the-art algorithms in clustering, link prediction, and visualization tasks.
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.