An unsupervised cluster-level based method for learning node representations of heterogeneous graphs in scientific papers

TL;DR

This paper introduces an unsupervised cluster-level method for learning node representations in heterogeneous scientific paper graphs, improving link prediction accuracy across various datasets.

Contribution

It proposes a novel unsupervised cluster-level approach (UCHL) for node embedding in heterogeneous graphs, enhancing scientific paper network analysis.

Findings

Achieves high performance on multiple evaluation metrics

Effective in capturing relationships between papers

Applicable to real scientific datasets

Abstract

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.