Abstract: Graph Contrastive Learning (GCL), a Self-Supervised Learning (SSL) architecture tailored for graphs, has shown notable potential for mitigating label scarcity. Its core idea is to amplify ...
Graph Neural Networks (GNNs) are proposed without considering the agnostic distribution shifts between training graphs and testing graphs, inducing the degeneration of the generalization ability of ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results