Graph Few-shot Learning via Knowledge Transfer
This addresses the challenge of low performance in graph neural networks when labeled nodes are scarce, which is an incremental improvement for graph learning applications.
The paper tackles the problem of semi-supervised node classification on graphs with limited labeled data by proposing a graph few-shot learning algorithm that transfers knowledge from auxiliary graphs to improve accuracy, achieving effectiveness demonstrated through experiments on four real-world datasets.
Towards the challenging problem of semi-supervised node classification, there have been extensive studies. As a frontier, Graph Neural Networks (GNNs) have aroused great interest recently, which update the representation of each node by aggregating information of its neighbors. However, most GNNs have shallow layers with a limited receptive field and may not achieve satisfactory performance especially when the number of labeled nodes is quite small. To address this challenge, we innovatively propose a graph few-shot learning (GFL) algorithm that incorporates prior knowledge learned from auxiliary graphs to improve classification accuracy on the target graph. Specifically, a transferable metric space characterized by a node embedding and a graph-specific prototype embedding function is shared between auxiliary graphs and the target, facilitating the transfer of structural knowledge. Extensive experiments and ablation studies on four real-world graph datasets demonstrate the effectiveness of our proposed model.