Multi-Task Graph Autoencoders
This work addresses the need for efficient and effective multi-task learning in graph representation learning, offering a versatile solution for applications like social network analysis and recommendation systems, though it is incremental in nature.
The paper tackles the problem of joint representation learning for link prediction and node classification on graphs by introducing a multi-task graph autoencoder that learns from both graph structure and node features. The model achieves significant improvements over three strong baselines across five benchmark datasets.
We examine two fundamental tasks associated with graph representation learning: link prediction and node classification. We present a new autoencoder architecture capable of learning a joint representation of local graph structure and available node features for the simultaneous multi-task learning of unsupervised link prediction and semi-supervised node classification. Our simple, yet effective and versatile model is efficiently trained end-to-end in a single stage, whereas previous related deep graph embedding methods require multiple training steps that are difficult to optimize. We provide an empirical evaluation of our model on five benchmark relational, graph-structured datasets and demonstrate significant improvement over three strong baselines for graph representation learning. Reference code and data are available at https://github.com/vuptran/graph-representation-learning