TLRM: Task-level Relation Module for GNN-based Few-Shot Learning

TL;DR

This paper introduces TLRM, a task-level relation module for GNN-based few-shot learning, which models the relation between samples and entire tasks, improving classification performance on benchmark datasets.

Contribution

The paper proposes a novel task-level relation module (TLRM) that captures sample-to-task relations, addressing limitations of sample-to-sample relation measures in GNN-based few-shot learning.

Findings

TLRM improves classification accuracy on four benchmark datasets.

Experimental results show the effectiveness of TLRM in GNN-based few-shot learning.

The module outperforms existing relation measurement methods.

Abstract

Recently, graph neural networks (GNNs) have shown powerful ability to handle few-shot classification problem, which aims at classifying unseen samples when trained with limited labeled samples per class. GNN-based few-shot learning architectures mostly replace traditional metric with a learnable GNN. In the GNN, the nodes are set as the samples embedding, and the relationship between two connected nodes can be obtained by a network, the input of which is the difference of their embedding features. We consider this method of measuring relation of samples only models the sample-to-sample relation, while neglects the specificity of different tasks. That is, this method of measuring relation does not take the task-level information into account. To this end, we propose a new relation measure method, namely the task-level relation module (TLRM), to explicitly model the task-level relation of one sample to all the others. The proposed module captures the relation representations between nodes by considering the sample-to-task instead of sample-to-sample embedding features. We conducted extensive experiments on four benchmark datasets: mini-ImageNet, tiered-ImageNet, CUB-$200$-$2011$, and CIFAR-FS. Experimental results demonstrate that the proposed module is effective for GNN-based few-shot learning.