MuL-GRN: Multi-Level Graph Relation Network for Few-Shot Node Classification

• Published in: IEEE transactions on knowledge and data engineering 2023-06, Vol.35 (6), p.6085-6098
• Main Authors: Zhang, Lingling, Wang, Shaowei, Liu, Jun, Chang, Xiaojun, Lin, Qika, Wu, Yaqiang, Zheng, Qinghua
• Format: Article
• Language: English
• Subjects: Annotations; Classification; Computer vision; Costs; Current measurement; Feature extraction; few-shot learning; Fuses; Graph neural networks; Graph theory; Knowledge acquisition; Learning; Modules; Network topology; Node classification; Nodes; subgraph relation; three-view relations
• ISSN: 1041-4347; 1558-2191
• DOI: 10.1109/TKDE.2022.3176880

Few-shot learning (FSL) that acquires new knowledge with little supervision, attracts much attention due to expensive cost of data annotation. Various meta-learning methods have made a great progress for few-shot problem in image and text data. In reality, data samples are not independent but rich in link relations. Large amounts of data exists in the form of graph structure such as citation, social, and biological networks. However, FSL study on graph data is still in its infancy because of the obstacle on extracting meta-knowledge from a meta node classification task. Current research simply combines the FSL methods experienced in computer vision with node representation models together, ignoring the effect of rich links among support and query nodes in few-shot meta-task. For this issue, we propose a novel Multi-Level Graph Relation Network (MuL-GRN) for the challenging few-shot node classification. MuL-GRN extracts node embeddings through the popular graph neural networks (GNNs). And it includes a relation learning module to mine the deep node relations from three views, namely node-level, global subgraph-level, and local subgraph-level relations. For any two nodes, the node-level relation is computed on their node embeddings, global subgraph-level relation is measured on their subgraph embeddings, and the local subgraph-level relation is mined according to the pairwise node comparison information in their subgraphs. The three-view relation vectors are fused together with an interesting relation fusion module, which measures the importance of relation vector for the current few-shot classification task automatically. Extensive experiments on five real datasets show that MuL-GRN significantly outperforms existing state-of-the-art methods by a large margin.