End-to-end open-set semi-supervised node classification with out-of-distribution detection

• Main Authors: HUANG, Tiancheng, WANG, Donglin, FANG, Yuan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Data Mining: Mining Graphs; Machine Learning: Semi-Supervised Learning; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/7479; https://ink.library.smu.edu.sg/context/sis_research/article/8482/viewcontent/IJCAI22_LMN.pdf
• Institution: Singapore Management University

Out-Of-Distribution (OOD) samples are prevalent in real-world applications. The OOD issue becomes even more severe on graph data, as the effect of OOD nodes can be potentially amplified by propagation through the graph topology. Recent works have considered the OOD detection problem, which is critic...