Hyperbolic graph topic modeling network with continuously updated topic tree

• Main Authors: ZHANG, Ce, YING, Rex, LAUW, Hady Wirawan
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2023
• 主題: Hyperbolic graph neural networks; Text mining; Topic modeling; Graphics and Human Computer Interfaces; OS and Networks
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8309; https://ink.library.smu.edu.sg/context/sis_research/article/9312/viewcontent/kdd23.pdf

Connectivity across documents often exhibits a hierarchical network structure. Hyperbolic Graph Neural Networks (HGNNs) have shown promise in preserving network hierarchy. However, they do not model the notion of topics, thus document representations lack semantic interpretability. On the other hand...