ResVGAE: Going Deeper with Residual Modules for Link Prediction
This work addresses link prediction in graph data, but it is incremental as it builds on existing graph autoencoder architectures with residual connections.
The authors tackled the problem of shallow graph autoencoders limiting multi-hop relation capture by proposing ResVGAE, a deep variational graph autoencoder with residual modules, which improved average precision and achieved results comparable to state-of-the-art methods.
Graph autoencoders are efficient at embedding graph-based data sets. Most graph autoencoder architectures have shallow depths which limits their ability to capture meaningful relations between nodes separated by multi-hops. In this paper, we propose Residual Variational Graph Autoencoder, ResVGAE, a deep variational graph autoencoder model with multiple residual modules. We show that our multiple residual modules, a convolutional layer with residual connection, improve the average precision of the graph autoencoders. Experimental results suggest that our proposed model with residual modules outperforms the models without residual modules and achieves similar results when compared with other state-of-the-art methods.