Universal Network Representation for Heterogeneous Information Networks
This addresses the limitation of existing methods that only handle homogeneous networks, enabling better analysis of complex, multi-type network data for applications like node classification and visualization.
The paper tackles the problem of representing nodes in heterogeneous information networks, where nodes are of different types, by proposing a universal network representation approach (UNRA) that achieves a 3% to 132% performance improvement in node classification accuracy compared to six state-of-the-art algorithms.
Network representation aims to represent the nodes in a network as continuous and compact vectors, and has attracted much attention in recent years due to its ability to capture complex structure relationships inside networks. However, existing network representation methods are commonly designed for homogeneous information networks where all the nodes (entities) of a network are of the same type, e.g., papers in a citation network. In this paper, we propose a universal network representation approach (UNRA), that represents different types of nodes in heterogeneous information networks in a continuous and common vector space. The UNRA is built on our latest mutually updated neural language module, which simultaneously captures inter-relationship among homogeneous nodes and node-content correlation. Relationships between different types of nodes are also assembled and learned in a unified framework. Experiments validate that the UNRA achieves outstanding performance, compared to six other state-of-the-art algorithms, in node representation, node classification, and network visualization. In node classification, the UNRA achieves a 3\% to 132\% performance improvement in terms of accuracy.