Graph Few-shot Learning via Knowledge Transfer
Graph Few-shot Learning via Knowledge Transfer
复制标题
DOI：
10.1609/aaai.v34i04.6142
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Huaxiu Yao;Chuxu Zhang;Ying Wei;Meng Jiang;Suhang Wang;Junzhou Huang;N. Chawla;Z. Li
中科院分区：
文献类型：
--
作者：
Huaxiu Yao;Chuxu Zhang;Ying Wei;Meng Jiang;Suhang Wang;Junzhou Huang;N. Chawla;Z. Li
对于半监督节点分类这一具有挑战性的问题，已经有了广泛的研究。图神经网络作为一个前沿领域，近年来引起了人们极大的兴趣，它通过聚集其邻居的信息来更新每个节点的表示。然而，大多数GNN具有有限接收场的浅层，并且可能无法实现令人满意的性能，特别是当标记节点的数量非常小时。为了应对这一挑战，我们创新性地提出了一种图少拍学习（GFL）算法，该算法结合了从辅助图中学习到的先验知识，以提高目标图的分类精度。具体而言，可转移的度量空间的特征在于节点嵌入和特定于图的原型嵌入功能之间的辅助图和目标共享，促进结构知识的转移。在四个真实世界的图数据集上进行的大量实验和消融研究证明了我们提出的模型的有效性和每个组件的贡献。
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 and the contribution of each component.