Complementary Supervised and Self-Supervised Representations for Out-of-Distribution Graph Learning
Out-of-distribution (OOD) generalization remains challenging for graph neural networks (GNNs), as graph distributions can vary substantially across time and domains. Supervised and self-supervised graph representation learning are guided by distinct objectives and offer different perspectives on graph representations....
Qing-Ying Hao, Zi-Kang Chen, Chu-Xuan Hu et al.
· 0 citations