Semantic Proximity Search on Heterogeneous Graph by Proximity Embedding

• DOI: 10.1609/aaai.v31i1.10486
• Publication Date: 2022-06-24T19:28:13Z
• Authors: Zemin Liu; Vincent W. Zheng; Zhou Zhao; Fanwei Zhu; Kevin Chen-Chuan ...; Minghui Wu; Jing Ying
• Keywords: Graph Embedding

Many real-world networks have a rich collection of objects. The semantics these objects allows us to capture different classes proximities, thus enabling an important task semantic proximity search. As the core search, we measure on heterogeneous graph, whose nodes are various types Most existing methods rely engineering features about graph structure between two their proximity. With recent development embedding, see good chance avoid feature for There is very little work using embedding We also observe that typically focus nodes, which "indirect'' approach learn Thus, introduce new concept directly embeds network possibly distant nodes. design our so as flexibly support both symmetric and asymmetric proximities. Based can easily estimate score enable search graph. evaluate method three public data sets, show it outperforms state-of-the-art baselines.