Iterative graph self-distillation

• المؤلفون الرئيسيون: ZHANG, Hanlin, LIN, Shuai, LIU, Weiyang, ZHOU, Pan, TANG, Jian, LIANG, Xiaodan, XING, Eric
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2024
• الموضوعات: graph representation learning; self-supervised learning; contrastive learning; Graphics and Human Computer Interfaces
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/8992; https://ink.library.smu.edu.sg/context/sis_research/article/9995/viewcontent/2023_TKDE_Self_Distillation.pdf

Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs. To address this, we propose a method called Iterative Graph Self-Distillation (IGSD) which learns graph-level representation in an unsupervised manner through instance discrimination using a se...