Learning Graph Representations with Embedding Propagation
This addresses graph representation learning for researchers and practitioners, offering a competitive and efficient method, though it appears incremental as it builds on existing message-passing techniques.
The authors tackled the problem of learning graph representations by proposing Embedding Propagation (EP), an unsupervised framework that uses forward and backward messages between nodes, and it often outperforms state-of-the-art methods on benchmark datasets with fewer parameters.
We propose Embedding Propagation (EP), an unsupervised learning framework for graph-structured data. EP learns vector representations of graphs by passing two types of messages between neighboring nodes. Forward messages consist of label representations such as representations of words and other attributes associated with the nodes. Backward messages consist of gradients that result from aggregating the label representations and applying a reconstruction loss. Node representations are finally computed from the representation of their labels. With significantly fewer parameters and hyperparameters an instance of EP is competitive with and often outperforms state of the art unsupervised and semi-supervised learning methods on a range of benchmark data sets.