An unsupervised cluster-level based method for learning node representations of heterogeneous graphs in scientific papers
This work addresses the challenge of representing nodes like authors and papers in scientific paper networks, but it appears incremental as it builds on existing heterogeneous graph methods without introducing a major breakthrough.
The paper tackled the problem of learning node representations in scientific paper heterogeneous graphs by proposing an unsupervised cluster-level method (UCHL), which achieved excellent performance on multiple evaluation metrics in link prediction tasks on real datasets.
Learning knowledge representation of scientific paper data is a problem to be solved, and how to learn the representation of paper nodes in scientific paper heterogeneous network is the core to solve this problem. This paper proposes an unsupervised cluster-level scientific paper heterogeneous graph node representation learning method (UCHL), aiming at obtaining the representation of nodes (authors, institutions, papers, etc.) in the heterogeneous graph of scientific papers. Based on the heterogeneous graph representation, this paper performs link prediction on the entire heterogeneous graph and obtains the relationship between the edges of the nodes, that is, the relationship between papers and papers. Experiments results show that the proposed method achieves excellent performance on multiple evaluation metrics on real scientific paper datasets.