Graph few-shot learning is of great importance among various graph learning tasks. Under thefew-shot scenario, models areoftenrequired toconduct classification givenlimited labeled samples. Existing graph few-shot learning methods typically leverage Graph Neural Networks (GNNs) and perform classification across a series of meta-tasks. Nevertheless, these methods generally rely on the original graph (i.e., the graph that the meta-task is sampled from) to learn node representations.

Interestingly, and in a sharp departure from previous proposals, this operation on coarsened graphs is often oriented, even when the original graph is undirected.

This prevailing paradigm heavily relies on the out-of-distribution (OOD) effect to influence the model's prediction.

This paper introduces a new Subgraph GNN framework to address these issues.

Graph convolution networks (GCNs) for recommendations haveemerged asan important research topic due to their ability to exploit higher-order neighbors. Despite their success, most of them suffer from the popularity bias brought by a small number of active users and popular items.