Document recommendation systems have traditionally relied upon high-dimensional vector representations that scale poorly in corpora with diverse vocabularies. Existing graph-based approaches focus on the metadata of documents and, unfortunately, ignore the content of the papers. In this work, researchers have designed and implemented a new system they call Graggle, which builds a graph to model a corpus. Nodes are papers, and edges represent significant words shared between them. We then leverage modern graph learning techniques to turn this graph into a highly efficient tool for dimensionality reduction. Documents are represented as low-dimensional vector embeddings generated with a graph autoencoder. Our experiments show that this approach outperforms traditional document vector-based and text autoencoding approaches on labeled data. Additionally, we have applied this technique to a repository of unlabeled research documents about the novel coronavirus to demonstrate its effectiveness as a real-world tool.
You can read more about the experiments in IEEE Xplore.