Learning to Make Predictions on Graphs with Autoencoders
This work addresses graph representation learning for tasks like link prediction and node classification, offering an incremental improvement in efficiency and performance over existing methods.
The paper tackles link prediction and node classification on graphs by introducing a novel autoencoder architecture that learns joint representations of graph structure and node features, achieving significant improvements over related methods on nine benchmark datasets.
We examine two fundamental tasks associated with graph representation learning: link prediction and semi-supervised node classification. We present a novel autoencoder architecture capable of learning a joint representation of both local graph structure and available node features for the multi-task learning of link prediction and node classification. Our autoencoder architecture is efficiently trained end-to-end in a single learning stage to simultaneously perform link prediction and node classification, whereas previous related methods require multiple training steps that are difficult to optimize. We provide a comprehensive empirical evaluation of our models on nine benchmark graph-structured datasets and demonstrate significant improvement over related methods for graph representation learning. Reference code and data are available at https://github.com/vuptran/graph-representation-learning