Contrastive pre-training of GNNs on heterogeneous graphs

• المؤلفون الرئيسيون: JIANG, Xunqiang, LU, Yuanfu, FANG, Yuan, SHI, Chuan
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2021
• الموضوعات: Pre-training; Heterogeneous graph; Self-supervised learning; Databases and Information Systems
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/6889; https://ink.library.smu.edu.sg/context/sis_research/article/7892/viewcontent/124.pdf

While graph neural networks (GNNs) emerge as the state-of-the-art representation learning methods on graphs, they often require a large amount of labeled data to achieve satisfactory performance, which is often expensive or unavailable. To relieve the label scarcity issue, some pre-training strategi...