Relative and absolute location embedding for few-shot node classification on graph

• Main Authors: LIU, Zemin, FANG, Yuan, LIU, Chenghao, HOI, Steven C. H.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: graph neural networks; few-shot learning; novel classes on graph; Artificial Intelligence and Robotics; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/6178; https://ink.library.smu.edu.sg/context/sis_research/article/7181/viewcontent/AAAI21_RALE.pdf
• Institution: Singapore Management University

Node classification is an important problem on graphs. While recent advances in graph neural networks achieve promising performance, they require abundant labeled nodes for training. However, in many practical scenarios there often exist novel classes in which only one or a few labeled nodes are ava...