%0 Journal Article %1 kipf_variational_2016 %A Kipf, Thomas N. %A Welling, Max %D 2016 %J arXiv:1611.07308 cs, stat %K graphembedding jn %T Variational Graph Auto-Encoders %U http://arxiv.org/abs/1611.07308 %X We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent representations for undirected graphs. We demonstrate this model using a graph convolutional network (GCN) encoder and a simple inner product decoder. Our model achieves competitive results on a link prediction task in citation networks. In contrast to most existing models for unsupervised learning on graph-structured data and link prediction, our model can naturally incorporate node features, which significantly improves predictive performance on a number of benchmark datasets.

@article{kipf_variational_2016, abstract = {We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent representations for undirected graphs. We demonstrate this model using a graph convolutional network (GCN) encoder and a simple inner product decoder. Our model achieves competitive results on a link prediction task in citation networks. In contrast to most existing models for unsupervised learning on graph-structured data and link prediction, our model can naturally incorporate node features, which significantly improves predictive performance on a number of benchmark datasets.}, added-at = {2020-08-20T09:49:10.000+0200}, author = {Kipf, Thomas N. and Welling, Max}, biburl = {https://www.bibsonomy.org/bibtex/2490764aa9061cba682f2a78a5033c172/julianneuberger}, file = {Kipf, Welling - Variational Graph Auto-Encoders.pdf:C\:\\Users\\Admin\\Documents\\Research\\_Paperbase\\Graph Embeddings\\Kipf, Welling - Variational Graph Auto-Encoders.pdf:application/pdf}, interhash = {47086987cecf0ec638e33452f7b96e0d}, intrahash = {490764aa9061cba682f2a78a5033c172}, journal = {arXiv:1611.07308 [cs, stat]}, keywords = {graphembedding jn}, language = {en}, month = nov, note = {arXiv: 1611.07308}, timestamp = {2020-08-20T09:49:30.000+0200}, title = {Variational Graph Auto-Encoders}, url = {http://arxiv.org/abs/1611.07308}, urldate = {2020-02-02}, year = 2016 }