.png){kind=icon}
.png){kind=icon}
Return
Graph Few-Shot Learning via Restructuring Task Graph
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3178849.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Existing graph few-shot learning (FSL) methods usually train a model on many task graphs and transfer the learned model to a new task graph. However, the task graphs often contain a great number of isolated nodes, which results in the severe deficiency of learned node embeddings. Furthermore, in the training process, the neglect of task information also constrains the model's expressive ability. In this brief, we propose a novel metric-based graph few-shot learning approach via restructuring task graph (GFL-RTG). To solve the problems above, we innovatively restructure the task graph by adding class nodes and a task node to the original individual task graph. We first add class nodes and determine the connectivity between class nodes and others via their similarity. Then, we utilize a graph pooling network to learn a task embedding, which is regarded as a task node. Finally, the new task graph is restructured by combining class nodes, task node, and original nodes, which is then used as input to the metric-based graph neural network (GNN) to conduct few-shot learning. Our extensive experiments on three graph-structured datasets demonstrate that our proposed method generally outperforms the state-of-the-art baselines in few-shot learning.
Keywords:
Task analysis
Training
Learning systems
Testing
Prototypes
Message passing
Graph neural networks
Aggregation
class node
graph few-shot learning (FSL)
graph neural networks (GNNs)
node classification
task graph
task node
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W