Graph Few-shot Learning via Knowledge Transfer

TL;DR

This paper introduces a graph few-shot learning algorithm that leverages prior knowledge from auxiliary graphs to enhance semi-supervised node classification, especially with limited labeled data.

Contribution

The paper proposes a novel GFL method using a transferable metric space and prototype embeddings to transfer structural knowledge from auxiliary graphs to the target.

Findings

Effective on four real-world datasets

Outperforms baseline methods in low-label scenarios

Ablation studies confirm the importance of transferred knowledge

Abstract

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.